Docs
Packagesgcp.dataplex.Datascan
Explore with Pulumi AI
Represents a user-visible job which provides the insights for the related data source.
To get more information about Datascan, see:
- API documentation
- How-to Guides
Example Usage
Dataplex Datascan Basic Profile
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
var basicProfile = new Gcp.DataPlex.Datascan("basicProfile", new()
{
Data = new Gcp.DataPlex.Inputs.DatascanDataArgs
{
Resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
},
DataProfileSpec = null,
DataScanId = "dataprofile-basic",
ExecutionSpec = new Gcp.DataPlex.Inputs.DatascanExecutionSpecArgs
{
Trigger = new Gcp.DataPlex.Inputs.DatascanExecutionSpecTriggerArgs
{
OnDemand = null,
},
},
Location = "us-central1",
Project = "my-project-name",
});
});
package main
import (
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/dataplex"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
_, err := dataplex.NewDatascan(ctx, "basicProfile", &dataplex.DatascanArgs{
Data: &dataplex.DatascanDataArgs{
Resource: pulumi.String("//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"),
},
DataProfileSpec: nil,
DataScanId: pulumi.String("dataprofile-basic"),
ExecutionSpec: &dataplex.DatascanExecutionSpecArgs{
Trigger: &dataplex.DatascanExecutionSpecTriggerArgs{
OnDemand: nil,
},
},
Location: pulumi.String("us-central1"),
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
return nil
})
}
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.dataplex.Datascan;
import com.pulumi.gcp.dataplex.DatascanArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataProfileSpecArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecTriggerArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecTriggerOnDemandArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
public static void main(String[] args) {
Pulumi.run(App::stack);
}
public static void stack(Context ctx) {
var basicProfile = new Datascan("basicProfile", DatascanArgs.builder()
.data(DatascanDataArgs.builder()
.resource("//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare")
.build())
.dataProfileSpec()
.dataScanId("dataprofile-basic")
.executionSpec(DatascanExecutionSpecArgs.builder()
.trigger(DatascanExecutionSpecTriggerArgs.builder()
.onDemand()
.build())
.build())
.location("us-central1")
.project("my-project-name")
.build());
}
}
import pulumi
import pulumi_gcp as gcp
basic_profile = gcp.dataplex.Datascan("basicProfile",
data=gcp.dataplex.DatascanDataArgs(
resource="//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
),
data_profile_spec=gcp.dataplex.DatascanDataProfileSpecArgs(),
data_scan_id="dataprofile-basic",
execution_spec=gcp.dataplex.DatascanExecutionSpecArgs(
trigger=gcp.dataplex.DatascanExecutionSpecTriggerArgs(
on_demand=gcp.dataplex.DatascanExecutionSpecTriggerOnDemandArgs(),
),
),
location="us-central1",
project="my-project-name")
import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
const basicProfile = new gcp.dataplex.Datascan("basicProfile", {
data: {
resource: "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
},
dataProfileSpec: {},
dataScanId: "dataprofile-basic",
executionSpec: {
trigger: {
onDemand: {},
},
},
location: "us-central1",
project: "my-project-name",
});
resources:
basicProfile:
type: gcp:dataplex:Datascan
properties:
data:
resource: //bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare
dataProfileSpec: {}
dataScanId: dataprofile-basic
executionSpec:
trigger:
onDemand: {}
location: us-central1
project: my-project-name
Dataplex Datascan Full Profile
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
var source = new Gcp.BigQuery.Dataset("source", new()
{
DatasetId = "dataplex_dataset",
FriendlyName = "test",
Description = "This is a test description",
Location = "US",
DeleteContentsOnDestroy = true,
});
var fullProfile = new Gcp.DataPlex.Datascan("fullProfile", new()
{
Location = "us-central1",
DisplayName = "Full Datascan Profile",
DataScanId = "dataprofile-full",
Description = "Example resource - Full Datascan Profile",
Labels =
{
{ "author", "billing" },
},
Data = new Gcp.DataPlex.Inputs.DatascanDataArgs
{
Resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
},
ExecutionSpec = new Gcp.DataPlex.Inputs.DatascanExecutionSpecArgs
{
Trigger = new Gcp.DataPlex.Inputs.DatascanExecutionSpecTriggerArgs
{
Schedule = new Gcp.DataPlex.Inputs.DatascanExecutionSpecTriggerScheduleArgs
{
Cron = "TZ=America/New_York 1 1 * * *",
},
},
},
DataProfileSpec = new Gcp.DataPlex.Inputs.DatascanDataProfileSpecArgs
{
SamplingPercent = 80,
RowFilter = "word_count > 10",
IncludeFields = new Gcp.DataPlex.Inputs.DatascanDataProfileSpecIncludeFieldsArgs
{
FieldNames = new[]
{
"word_count",
},
},
ExcludeFields = new Gcp.DataPlex.Inputs.DatascanDataProfileSpecExcludeFieldsArgs
{
FieldNames = new[]
{
"property_type",
},
},
PostScanActions = new Gcp.DataPlex.Inputs.DatascanDataProfileSpecPostScanActionsArgs
{
BigqueryExport = new Gcp.DataPlex.Inputs.DatascanDataProfileSpecPostScanActionsBigqueryExportArgs
{
ResultsTable = "//bigquery.googleapis.com/projects/my-project-name/datasets/dataplex_dataset/tables/profile_export",
},
},
},
Project = "my-project-name",
}, new CustomResourceOptions
{
DependsOn = new[]
{
source,
},
});
});
package main
import (
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/bigquery"
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/dataplex"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
source, err := bigquery.NewDataset(ctx, "source", &bigquery.DatasetArgs{
DatasetId: pulumi.String("dataplex_dataset"),
FriendlyName: pulumi.String("test"),
Description: pulumi.String("This is a test description"),
Location: pulumi.String("US"),
DeleteContentsOnDestroy: pulumi.Bool(true),
})
if err != nil {
return err
}
_, err = dataplex.NewDatascan(ctx, "fullProfile", &dataplex.DatascanArgs{
Location: pulumi.String("us-central1"),
DisplayName: pulumi.String("Full Datascan Profile"),
DataScanId: pulumi.String("dataprofile-full"),
Description: pulumi.String("Example resource - Full Datascan Profile"),
Labels: pulumi.StringMap{
"author": pulumi.String("billing"),
},
Data: &dataplex.DatascanDataArgs{
Resource: pulumi.String("//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"),
},
ExecutionSpec: &dataplex.DatascanExecutionSpecArgs{
Trigger: &dataplex.DatascanExecutionSpecTriggerArgs{
Schedule: &dataplex.DatascanExecutionSpecTriggerScheduleArgs{
Cron: pulumi.String("TZ=America/New_York 1 1 * * *"),
},
},
},
DataProfileSpec: &dataplex.DatascanDataProfileSpecArgs{
SamplingPercent: pulumi.Float64(80),
RowFilter: pulumi.String("word_count > 10"),
IncludeFields: &dataplex.DatascanDataProfileSpecIncludeFieldsArgs{
FieldNames: pulumi.StringArray{
pulumi.String("word_count"),
},
},
ExcludeFields: &dataplex.DatascanDataProfileSpecExcludeFieldsArgs{
FieldNames: pulumi.StringArray{
pulumi.String("property_type"),
},
},
PostScanActions: &dataplex.DatascanDataProfileSpecPostScanActionsArgs{
BigqueryExport: &dataplex.DatascanDataProfileSpecPostScanActionsBigqueryExportArgs{
ResultsTable: pulumi.String("//bigquery.googleapis.com/projects/my-project-name/datasets/dataplex_dataset/tables/profile_export"),
},
},
},
Project: pulumi.String("my-project-name"),
}, pulumi.DependsOn([]pulumi.Resource{
source,
}))
if err != nil {
return err
}
return nil
})
}
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.bigquery.Dataset;
import com.pulumi.gcp.bigquery.DatasetArgs;
import com.pulumi.gcp.dataplex.Datascan;
import com.pulumi.gcp.dataplex.DatascanArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecTriggerArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecTriggerScheduleArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataProfileSpecArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataProfileSpecIncludeFieldsArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataProfileSpecExcludeFieldsArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataProfileSpecPostScanActionsArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataProfileSpecPostScanActionsBigqueryExportArgs;
import com.pulumi.resources.CustomResourceOptions;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
public static void main(String[] args) {
Pulumi.run(App::stack);
}
public static void stack(Context ctx) {
var source = new Dataset("source", DatasetArgs.builder()
.datasetId("dataplex_dataset")
.friendlyName("test")
.description("This is a test description")
.location("US")
.deleteContentsOnDestroy(true)
.build());
var fullProfile = new Datascan("fullProfile", DatascanArgs.builder()
.location("us-central1")
.displayName("Full Datascan Profile")
.dataScanId("dataprofile-full")
.description("Example resource - Full Datascan Profile")
.labels(Map.of("author", "billing"))
.data(DatascanDataArgs.builder()
.resource("//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare")
.build())
.executionSpec(DatascanExecutionSpecArgs.builder()
.trigger(DatascanExecutionSpecTriggerArgs.builder()
.schedule(DatascanExecutionSpecTriggerScheduleArgs.builder()
.cron("TZ=America/New_York 1 1 * * *")
.build())
.build())
.build())
.dataProfileSpec(DatascanDataProfileSpecArgs.builder()
.samplingPercent(80)
.rowFilter("word_count > 10")
.includeFields(DatascanDataProfileSpecIncludeFieldsArgs.builder()
.fieldNames("word_count")
.build())
.excludeFields(DatascanDataProfileSpecExcludeFieldsArgs.builder()
.fieldNames("property_type")
.build())
.postScanActions(DatascanDataProfileSpecPostScanActionsArgs.builder()
.bigqueryExport(DatascanDataProfileSpecPostScanActionsBigqueryExportArgs.builder()
.resultsTable("//bigquery.googleapis.com/projects/my-project-name/datasets/dataplex_dataset/tables/profile_export")
.build())
.build())
.build())
.project("my-project-name")
.build(), CustomResourceOptions.builder()
.dependsOn(source)
.build());
}
}
import pulumi
import pulumi_gcp as gcp
source = gcp.bigquery.Dataset("source",
dataset_id="dataplex_dataset",
friendly_name="test",
description="This is a test description",
location="US",
delete_contents_on_destroy=True)
full_profile = gcp.dataplex.Datascan("fullProfile",
location="us-central1",
display_name="Full Datascan Profile",
data_scan_id="dataprofile-full",
description="Example resource - Full Datascan Profile",
labels={
"author": "billing",
},
data=gcp.dataplex.DatascanDataArgs(
resource="//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
),
execution_spec=gcp.dataplex.DatascanExecutionSpecArgs(
trigger=gcp.dataplex.DatascanExecutionSpecTriggerArgs(
schedule=gcp.dataplex.DatascanExecutionSpecTriggerScheduleArgs(
cron="TZ=America/New_York 1 1 * * *",
),
),
),
data_profile_spec=gcp.dataplex.DatascanDataProfileSpecArgs(
sampling_percent=80,
row_filter="word_count > 10",
include_fields=gcp.dataplex.DatascanDataProfileSpecIncludeFieldsArgs(
field_names=["word_count"],
),
exclude_fields=gcp.dataplex.DatascanDataProfileSpecExcludeFieldsArgs(
field_names=["property_type"],
),
post_scan_actions=gcp.dataplex.DatascanDataProfileSpecPostScanActionsArgs(
bigquery_export=gcp.dataplex.DatascanDataProfileSpecPostScanActionsBigqueryExportArgs(
results_table="//bigquery.googleapis.com/projects/my-project-name/datasets/dataplex_dataset/tables/profile_export",
),
),
),
project="my-project-name",
opts=pulumi.ResourceOptions(depends_on=[source]))
import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
const source = new gcp.bigquery.Dataset("source", {
datasetId: "dataplex_dataset",
friendlyName: "test",
description: "This is a test description",
location: "US",
deleteContentsOnDestroy: true,
});
const fullProfile = new gcp.dataplex.Datascan("fullProfile", {
location: "us-central1",
displayName: "Full Datascan Profile",
dataScanId: "dataprofile-full",
description: "Example resource - Full Datascan Profile",
labels: {
author: "billing",
},
data: {
resource: "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
},
executionSpec: {
trigger: {
schedule: {
cron: "TZ=America/New_York 1 1 * * *",
},
},
},
dataProfileSpec: {
samplingPercent: 80,
rowFilter: "word_count > 10",
includeFields: {
fieldNames: ["word_count"],
},
excludeFields: {
fieldNames: ["property_type"],
},
postScanActions: {
bigqueryExport: {
resultsTable: "//bigquery.googleapis.com/projects/my-project-name/datasets/dataplex_dataset/tables/profile_export",
},
},
},
project: "my-project-name",
}, {
dependsOn: [source],
});
resources:
fullProfile:
type: gcp:dataplex:Datascan
properties:
location: us-central1
displayName: Full Datascan Profile
dataScanId: dataprofile-full
description: Example resource - Full Datascan Profile
labels:
author: billing
data:
resource: //bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare
executionSpec:
trigger:
schedule:
cron: TZ=America/New_York 1 1 * * *
dataProfileSpec:
samplingPercent: 80
rowFilter: word_count > 10
includeFields:
fieldNames:
- word_count
excludeFields:
fieldNames:
- property_type
postScanActions:
bigqueryExport:
resultsTable: //bigquery.googleapis.com/projects/my-project-name/datasets/dataplex_dataset/tables/profile_export
project: my-project-name
options:
dependson:
- ${source}
source:
type: gcp:bigquery:Dataset
properties:
datasetId: dataplex_dataset
friendlyName: test
description: This is a test description
location: US
deleteContentsOnDestroy: true
Dataplex Datascan Basic Quality
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
var basicQuality = new Gcp.DataPlex.Datascan("basicQuality", new()
{
Data = new Gcp.DataPlex.Inputs.DatascanDataArgs
{
Resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
},
DataQualitySpec = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecArgs
{
Rules = new[]
{
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Description = "rule 1 for validity dimension",
Dimension = "VALIDITY",
Name = "rule1",
TableConditionExpectation = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleTableConditionExpectationArgs
{
SqlExpression = "COUNT(*) > 0",
},
},
},
},
DataScanId = "dataquality-basic",
ExecutionSpec = new Gcp.DataPlex.Inputs.DatascanExecutionSpecArgs
{
Trigger = new Gcp.DataPlex.Inputs.DatascanExecutionSpecTriggerArgs
{
OnDemand = null,
},
},
Location = "us-central1",
Project = "my-project-name",
});
});
package main
import (
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/dataplex"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
_, err := dataplex.NewDatascan(ctx, "basicQuality", &dataplex.DatascanArgs{
Data: &dataplex.DatascanDataArgs{
Resource: pulumi.String("//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"),
},
DataQualitySpec: &dataplex.DatascanDataQualitySpecArgs{
Rules: dataplex.DatascanDataQualitySpecRuleArray{
&dataplex.DatascanDataQualitySpecRuleArgs{
Description: pulumi.String("rule 1 for validity dimension"),
Dimension: pulumi.String("VALIDITY"),
Name: pulumi.String("rule1"),
TableConditionExpectation: &dataplex.DatascanDataQualitySpecRuleTableConditionExpectationArgs{
SqlExpression: pulumi.String("COUNT(*) > 0"),
},
},
},
},
DataScanId: pulumi.String("dataquality-basic"),
ExecutionSpec: &dataplex.DatascanExecutionSpecArgs{
Trigger: &dataplex.DatascanExecutionSpecTriggerArgs{
OnDemand: nil,
},
},
Location: pulumi.String("us-central1"),
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
return nil
})
}
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.dataplex.Datascan;
import com.pulumi.gcp.dataplex.DatascanArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataQualitySpecArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecTriggerArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecTriggerOnDemandArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
public static void main(String[] args) {
Pulumi.run(App::stack);
}
public static void stack(Context ctx) {
var basicQuality = new Datascan("basicQuality", DatascanArgs.builder()
.data(DatascanDataArgs.builder()
.resource("//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare")
.build())
.dataQualitySpec(DatascanDataQualitySpecArgs.builder()
.rules(DatascanDataQualitySpecRuleArgs.builder()
.description("rule 1 for validity dimension")
.dimension("VALIDITY")
.name("rule1")
.tableConditionExpectation(DatascanDataQualitySpecRuleTableConditionExpectationArgs.builder()
.sqlExpression("COUNT(*) > 0")
.build())
.build())
.build())
.dataScanId("dataquality-basic")
.executionSpec(DatascanExecutionSpecArgs.builder()
.trigger(DatascanExecutionSpecTriggerArgs.builder()
.onDemand()
.build())
.build())
.location("us-central1")
.project("my-project-name")
.build());
}
}
import pulumi
import pulumi_gcp as gcp
basic_quality = gcp.dataplex.Datascan("basicQuality",
data=gcp.dataplex.DatascanDataArgs(
resource="//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
),
data_quality_spec=gcp.dataplex.DatascanDataQualitySpecArgs(
rules=[gcp.dataplex.DatascanDataQualitySpecRuleArgs(
description="rule 1 for validity dimension",
dimension="VALIDITY",
name="rule1",
table_condition_expectation=gcp.dataplex.DatascanDataQualitySpecRuleTableConditionExpectationArgs(
sql_expression="COUNT(*) > 0",
),
)],
),
data_scan_id="dataquality-basic",
execution_spec=gcp.dataplex.DatascanExecutionSpecArgs(
trigger=gcp.dataplex.DatascanExecutionSpecTriggerArgs(
on_demand=gcp.dataplex.DatascanExecutionSpecTriggerOnDemandArgs(),
),
),
location="us-central1",
project="my-project-name")
import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
const basicQuality = new gcp.dataplex.Datascan("basicQuality", {
data: {
resource: "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare",
},
dataQualitySpec: {
rules: [{
description: "rule 1 for validity dimension",
dimension: "VALIDITY",
name: "rule1",
tableConditionExpectation: {
sqlExpression: "COUNT(*) > 0",
},
}],
},
dataScanId: "dataquality-basic",
executionSpec: {
trigger: {
onDemand: {},
},
},
location: "us-central1",
project: "my-project-name",
});
resources:
basicQuality:
type: gcp:dataplex:Datascan
properties:
data:
resource: //bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare
dataQualitySpec:
rules:
- description: rule 1 for validity dimension
dimension: VALIDITY
name: rule1
tableConditionExpectation:
sqlExpression: COUNT(*) > 0
dataScanId: dataquality-basic
executionSpec:
trigger:
onDemand: {}
location: us-central1
project: my-project-name
Dataplex Datascan Full Quality
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
var fullQuality = new Gcp.DataPlex.Datascan("fullQuality", new()
{
Data = new Gcp.DataPlex.Inputs.DatascanDataArgs
{
Resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/austin_bikeshare/tables/bikeshare_stations",
},
DataQualitySpec = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecArgs
{
RowFilter = "station_id > 1000",
Rules = new[]
{
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Column = "address",
Dimension = "VALIDITY",
NonNullExpectation = null,
Threshold = 0.99,
},
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Column = "council_district",
Dimension = "VALIDITY",
IgnoreNull = true,
RangeExpectation = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleRangeExpectationArgs
{
MaxValue = "10",
MinValue = "1",
StrictMaxEnabled = false,
StrictMinEnabled = true,
},
Threshold = 0.9,
},
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Column = "power_type",
Dimension = "VALIDITY",
IgnoreNull = false,
RegexExpectation = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleRegexExpectationArgs
{
Regex = ".*solar.*",
},
},
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Column = "property_type",
Dimension = "VALIDITY",
IgnoreNull = false,
SetExpectation = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleSetExpectationArgs
{
Values = new[]
{
"sidewalk",
"parkland",
},
},
},
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Column = "address",
Dimension = "UNIQUENESS",
UniquenessExpectation = null,
},
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Column = "number_of_docks",
Dimension = "VALIDITY",
StatisticRangeExpectation = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleStatisticRangeExpectationArgs
{
MaxValue = "15",
MinValue = "5",
Statistic = "MEAN",
StrictMaxEnabled = true,
StrictMinEnabled = true,
},
},
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Column = "footprint_length",
Dimension = "VALIDITY",
RowConditionExpectation = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleRowConditionExpectationArgs
{
SqlExpression = "footprint_length > 0 AND footprint_length <= 10",
},
},
new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleArgs
{
Dimension = "VALIDITY",
TableConditionExpectation = new Gcp.DataPlex.Inputs.DatascanDataQualitySpecRuleTableConditionExpectationArgs
{
SqlExpression = "COUNT(*) > 0",
},
},
},
SamplingPercent = 5,
},
DataScanId = "dataquality-full",
Description = "Example resource - Full Datascan Quality",
DisplayName = "Full Datascan Quality",
ExecutionSpec = new Gcp.DataPlex.Inputs.DatascanExecutionSpecArgs
{
Field = "modified_date",
Trigger = new Gcp.DataPlex.Inputs.DatascanExecutionSpecTriggerArgs
{
Schedule = new Gcp.DataPlex.Inputs.DatascanExecutionSpecTriggerScheduleArgs
{
Cron = "TZ=America/New_York 1 1 * * *",
},
},
},
Labels =
{
{ "author", "billing" },
},
Location = "us-central1",
Project = "my-project-name",
});
});
package main
import (
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/dataplex"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
_, err := dataplex.NewDatascan(ctx, "fullQuality", &dataplex.DatascanArgs{
Data: &dataplex.DatascanDataArgs{
Resource: pulumi.String("//bigquery.googleapis.com/projects/bigquery-public-data/datasets/austin_bikeshare/tables/bikeshare_stations"),
},
DataQualitySpec: &dataplex.DatascanDataQualitySpecArgs{
RowFilter: pulumi.String("station_id > 1000"),
Rules: dataplex.DatascanDataQualitySpecRuleArray{
&dataplex.DatascanDataQualitySpecRuleArgs{
Column: pulumi.String("address"),
Dimension: pulumi.String("VALIDITY"),
NonNullExpectation: nil,
Threshold: pulumi.Float64(0.99),
},
&dataplex.DatascanDataQualitySpecRuleArgs{
Column: pulumi.String("council_district"),
Dimension: pulumi.String("VALIDITY"),
IgnoreNull: pulumi.Bool(true),
RangeExpectation: &dataplex.DatascanDataQualitySpecRuleRangeExpectationArgs{
MaxValue: pulumi.String("10"),
MinValue: pulumi.String("1"),
StrictMaxEnabled: pulumi.Bool(false),
StrictMinEnabled: pulumi.Bool(true),
},
Threshold: pulumi.Float64(0.9),
},
&dataplex.DatascanDataQualitySpecRuleArgs{
Column: pulumi.String("power_type"),
Dimension: pulumi.String("VALIDITY"),
IgnoreNull: pulumi.Bool(false),
RegexExpectation: &dataplex.DatascanDataQualitySpecRuleRegexExpectationArgs{
Regex: pulumi.String(".*solar.*"),
},
},
&dataplex.DatascanDataQualitySpecRuleArgs{
Column: pulumi.String("property_type"),
Dimension: pulumi.String("VALIDITY"),
IgnoreNull: pulumi.Bool(false),
SetExpectation: &dataplex.DatascanDataQualitySpecRuleSetExpectationArgs{
Values: pulumi.StringArray{
pulumi.String("sidewalk"),
pulumi.String("parkland"),
},
},
},
&dataplex.DatascanDataQualitySpecRuleArgs{
Column: pulumi.String("address"),
Dimension: pulumi.String("UNIQUENESS"),
UniquenessExpectation: nil,
},
&dataplex.DatascanDataQualitySpecRuleArgs{
Column: pulumi.String("number_of_docks"),
Dimension: pulumi.String("VALIDITY"),
StatisticRangeExpectation: &dataplex.DatascanDataQualitySpecRuleStatisticRangeExpectationArgs{
MaxValue: pulumi.String("15"),
MinValue: pulumi.String("5"),
Statistic: pulumi.String("MEAN"),
StrictMaxEnabled: pulumi.Bool(true),
StrictMinEnabled: pulumi.Bool(true),
},
},
&dataplex.DatascanDataQualitySpecRuleArgs{
Column: pulumi.String("footprint_length"),
Dimension: pulumi.String("VALIDITY"),
RowConditionExpectation: &dataplex.DatascanDataQualitySpecRuleRowConditionExpectationArgs{
SqlExpression: pulumi.String("footprint_length > 0 AND footprint_length <= 10"),
},
},
&dataplex.DatascanDataQualitySpecRuleArgs{
Dimension: pulumi.String("VALIDITY"),
TableConditionExpectation: &dataplex.DatascanDataQualitySpecRuleTableConditionExpectationArgs{
SqlExpression: pulumi.String("COUNT(*) > 0"),
},
},
},
SamplingPercent: pulumi.Float64(5),
},
DataScanId: pulumi.String("dataquality-full"),
Description: pulumi.String("Example resource - Full Datascan Quality"),
DisplayName: pulumi.String("Full Datascan Quality"),
ExecutionSpec: &dataplex.DatascanExecutionSpecArgs{
Field: pulumi.String("modified_date"),
Trigger: &dataplex.DatascanExecutionSpecTriggerArgs{
Schedule: &dataplex.DatascanExecutionSpecTriggerScheduleArgs{
Cron: pulumi.String("TZ=America/New_York 1 1 * * *"),
},
},
},
Labels: pulumi.StringMap{
"author": pulumi.String("billing"),
},
Location: pulumi.String("us-central1"),
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
return nil
})
}
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.dataplex.Datascan;
import com.pulumi.gcp.dataplex.DatascanArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanDataQualitySpecArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecTriggerArgs;
import com.pulumi.gcp.dataplex.inputs.DatascanExecutionSpecTriggerScheduleArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
public static void main(String[] args) {
Pulumi.run(App::stack);
}
public static void stack(Context ctx) {
var fullQuality = new Datascan("fullQuality", DatascanArgs.builder()
.data(DatascanDataArgs.builder()
.resource("//bigquery.googleapis.com/projects/bigquery-public-data/datasets/austin_bikeshare/tables/bikeshare_stations")
.build())
.dataQualitySpec(DatascanDataQualitySpecArgs.builder()
.rowFilter("station_id > 1000")
.rules(
DatascanDataQualitySpecRuleArgs.builder()
.column("address")
.dimension("VALIDITY")
.nonNullExpectation()
.threshold(0.99)
.build(),
DatascanDataQualitySpecRuleArgs.builder()
.column("council_district")
.dimension("VALIDITY")
.ignoreNull(true)
.rangeExpectation(DatascanDataQualitySpecRuleRangeExpectationArgs.builder()
.maxValue(10)
.minValue(1)
.strictMaxEnabled(false)
.strictMinEnabled(true)
.build())
.threshold(0.9)
.build(),
DatascanDataQualitySpecRuleArgs.builder()
.column("power_type")
.dimension("VALIDITY")
.ignoreNull(false)
.regexExpectation(DatascanDataQualitySpecRuleRegexExpectationArgs.builder()
.regex(".*solar.*")
.build())
.build(),
DatascanDataQualitySpecRuleArgs.builder()
.column("property_type")
.dimension("VALIDITY")
.ignoreNull(false)
.setExpectation(DatascanDataQualitySpecRuleSetExpectationArgs.builder()
.values(
"sidewalk",
"parkland")
.build())
.build(),
DatascanDataQualitySpecRuleArgs.builder()
.column("address")
.dimension("UNIQUENESS")
.uniquenessExpectation()
.build(),
DatascanDataQualitySpecRuleArgs.builder()
.column("number_of_docks")
.dimension("VALIDITY")
.statisticRangeExpectation(DatascanDataQualitySpecRuleStatisticRangeExpectationArgs.builder()
.maxValue(15)
.minValue(5)
.statistic("MEAN")
.strictMaxEnabled(true)
.strictMinEnabled(true)
.build())
.build(),
DatascanDataQualitySpecRuleArgs.builder()
.column("footprint_length")
.dimension("VALIDITY")
.rowConditionExpectation(DatascanDataQualitySpecRuleRowConditionExpectationArgs.builder()
.sqlExpression("footprint_length > 0 AND footprint_length <= 10")
.build())
.build(),
DatascanDataQualitySpecRuleArgs.builder()
.dimension("VALIDITY")
.tableConditionExpectation(DatascanDataQualitySpecRuleTableConditionExpectationArgs.builder()
.sqlExpression("COUNT(*) > 0")
.build())
.build())
.samplingPercent(5)
.build())
.dataScanId("dataquality-full")
.description("Example resource - Full Datascan Quality")
.displayName("Full Datascan Quality")
.executionSpec(DatascanExecutionSpecArgs.builder()
.field("modified_date")
.trigger(DatascanExecutionSpecTriggerArgs.builder()
.schedule(DatascanExecutionSpecTriggerScheduleArgs.builder()
.cron("TZ=America/New_York 1 1 * * *")
.build())
.build())
.build())
.labels(Map.of("author", "billing"))
.location("us-central1")
.project("my-project-name")
.build());
}
}
import pulumi
import pulumi_gcp as gcp
full_quality = gcp.dataplex.Datascan("fullQuality",
data=gcp.dataplex.DatascanDataArgs(
resource="//bigquery.googleapis.com/projects/bigquery-public-data/datasets/austin_bikeshare/tables/bikeshare_stations",
),
data_quality_spec=gcp.dataplex.DatascanDataQualitySpecArgs(
row_filter="station_id > 1000",
rules=[
gcp.dataplex.DatascanDataQualitySpecRuleArgs(
column="address",
dimension="VALIDITY",
non_null_expectation=gcp.dataplex.DatascanDataQualitySpecRuleNonNullExpectationArgs(),
threshold=0.99,
),
gcp.dataplex.DatascanDataQualitySpecRuleArgs(
column="council_district",
dimension="VALIDITY",
ignore_null=True,
range_expectation=gcp.dataplex.DatascanDataQualitySpecRuleRangeExpectationArgs(
max_value="10",
min_value="1",
strict_max_enabled=False,
strict_min_enabled=True,
),
threshold=0.9,
),
gcp.dataplex.DatascanDataQualitySpecRuleArgs(
column="power_type",
dimension="VALIDITY",
ignore_null=False,
regex_expectation=gcp.dataplex.DatascanDataQualitySpecRuleRegexExpectationArgs(
regex=".*solar.*",
),
),
gcp.dataplex.DatascanDataQualitySpecRuleArgs(
column="property_type",
dimension="VALIDITY",
ignore_null=False,
set_expectation=gcp.dataplex.DatascanDataQualitySpecRuleSetExpectationArgs(
values=[
"sidewalk",
"parkland",
],
),
),
gcp.dataplex.DatascanDataQualitySpecRuleArgs(
column="address",
dimension="UNIQUENESS",
uniqueness_expectation=gcp.dataplex.DatascanDataQualitySpecRuleUniquenessExpectationArgs(),
),
gcp.dataplex.DatascanDataQualitySpecRuleArgs(
column="number_of_docks",
dimension="VALIDITY",
statistic_range_expectation=gcp.dataplex.DatascanDataQualitySpecRuleStatisticRangeExpectationArgs(
max_value="15",
min_value="5",
statistic="MEAN",
strict_max_enabled=True,
strict_min_enabled=True,
),
),
gcp.dataplex.DatascanDataQualitySpecRuleArgs(
column="footprint_length",
dimension="VALIDITY",
row_condition_expectation=gcp.dataplex.DatascanDataQualitySpecRuleRowConditionExpectationArgs(
sql_expression="footprint_length > 0 AND footprint_length <= 10",
),
),
gcp.dataplex.DatascanDataQualitySpecRuleArgs(
dimension="VALIDITY",
table_condition_expectation=gcp.dataplex.DatascanDataQualitySpecRuleTableConditionExpectationArgs(
sql_expression="COUNT(*) > 0",
),
),
],
sampling_percent=5,
),
data_scan_id="dataquality-full",
description="Example resource - Full Datascan Quality",
display_name="Full Datascan Quality",
execution_spec=gcp.dataplex.DatascanExecutionSpecArgs(
field="modified_date",
trigger=gcp.dataplex.DatascanExecutionSpecTriggerArgs(
schedule=gcp.dataplex.DatascanExecutionSpecTriggerScheduleArgs(
cron="TZ=America/New_York 1 1 * * *",
),
),
),
labels={
"author": "billing",
},
location="us-central1",
project="my-project-name")
import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
const fullQuality = new gcp.dataplex.Datascan("fullQuality", {
data: {
resource: "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/austin_bikeshare/tables/bikeshare_stations",
},
dataQualitySpec: {
rowFilter: "station_id > 1000",
rules: [
{
column: "address",
dimension: "VALIDITY",
nonNullExpectation: {},
threshold: 0.99,
},
{
column: "council_district",
dimension: "VALIDITY",
ignoreNull: true,
rangeExpectation: {
maxValue: "10",
minValue: "1",
strictMaxEnabled: false,
strictMinEnabled: true,
},
threshold: 0.9,
},
{
column: "power_type",
dimension: "VALIDITY",
ignoreNull: false,
regexExpectation: {
regex: ".*solar.*",
},
},
{
column: "property_type",
dimension: "VALIDITY",
ignoreNull: false,
setExpectation: {
values: [
"sidewalk",
"parkland",
],
},
},
{
column: "address",
dimension: "UNIQUENESS",
uniquenessExpectation: {},
},
{
column: "number_of_docks",
dimension: "VALIDITY",
statisticRangeExpectation: {
maxValue: "15",
minValue: "5",
statistic: "MEAN",
strictMaxEnabled: true,
strictMinEnabled: true,
},
},
{
column: "footprint_length",
dimension: "VALIDITY",
rowConditionExpectation: {
sqlExpression: "footprint_length > 0 AND footprint_length <= 10",
},
},
{
dimension: "VALIDITY",
tableConditionExpectation: {
sqlExpression: "COUNT(*) > 0",
},
},
],
samplingPercent: 5,
},
dataScanId: "dataquality-full",
description: "Example resource - Full Datascan Quality",
displayName: "Full Datascan Quality",
executionSpec: {
field: "modified_date",
trigger: {
schedule: {
cron: "TZ=America/New_York 1 1 * * *",
},
},
},
labels: {
author: "billing",
},
location: "us-central1",
project: "my-project-name",
});
resources:
fullQuality:
type: gcp:dataplex:Datascan
properties:
data:
resource: //bigquery.googleapis.com/projects/bigquery-public-data/datasets/austin_bikeshare/tables/bikeshare_stations
dataQualitySpec:
rowFilter: station_id > 1000
rules:
- column: address
dimension: VALIDITY
nonNullExpectation: {}
threshold: 0.99
- column: council_district
dimension: VALIDITY
ignoreNull: true
rangeExpectation:
maxValue: 10
minValue: 1
strictMaxEnabled: false
strictMinEnabled: true
threshold: 0.9
- column: power_type
dimension: VALIDITY
ignoreNull: false
regexExpectation:
regex: .*solar.*
- column: property_type
dimension: VALIDITY
ignoreNull: false
setExpectation:
values:
- sidewalk
- parkland
- column: address
dimension: UNIQUENESS
uniquenessExpectation: {}
- column: number_of_docks
dimension: VALIDITY
statisticRangeExpectation:
maxValue: 15
minValue: 5
statistic: MEAN
strictMaxEnabled: true
strictMinEnabled: true
- column: footprint_length
dimension: VALIDITY
rowConditionExpectation:
sqlExpression: footprint_length > 0 AND footprint_length <= 10
- dimension: VALIDITY
tableConditionExpectation:
sqlExpression: COUNT(*) > 0
samplingPercent: 5
dataScanId: dataquality-full
description: Example resource - Full Datascan Quality
displayName: Full Datascan Quality
executionSpec:
field: modified_date
trigger:
schedule:
cron: TZ=America/New_York 1 1 * * *
labels:
author: billing
location: us-central1
project: my-project-name
Create Datascan Resource
new Datascan(name: string, args: DatascanArgs, opts?: CustomResourceOptions);@overload
def Datascan(resource_name: str,
opts: Optional[ResourceOptions] = None,
data: Optional[DatascanDataArgs] = None,
data_profile_spec: Optional[DatascanDataProfileSpecArgs] = None,
data_quality_spec: Optional[DatascanDataQualitySpecArgs] = None,
data_scan_id: Optional[str] = None,
description: Optional[str] = None,
display_name: Optional[str] = None,
execution_spec: Optional[DatascanExecutionSpecArgs] = None,
labels: Optional[Mapping[str, str]] = None,
location: Optional[str] = None,
project: Optional[str] = None)
@overload
def Datascan(resource_name: str,
args: DatascanArgs,
opts: Optional[ResourceOptions] = None)func NewDatascan(ctx *Context, name string, args DatascanArgs, opts ...ResourceOption) (*Datascan, error)public Datascan(string name, DatascanArgs args, CustomResourceOptions? opts = null)
public Datascan(String name, DatascanArgs args)
public Datascan(String name, DatascanArgs args, CustomResourceOptions options)
type: gcp:dataplex:Datascan
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args DatascanArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resource.
- args DatascanArgs
- The arguments to resource properties.
- opts ResourceOptions
- Bag of options to control resource's behavior.
- ctx Context
- Context object for the current deployment.
- name string
- The unique name of the resource.
- args DatascanArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args DatascanArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args DatascanArgs
- The arguments to resource properties.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
Datascan Resource Properties
To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.
Inputs
The Datascan resource accepts the following input properties:
- Data
Datascan
Data The data source for DataScan. Structure is documented below.
- Data
Scan stringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- Execution
Spec DatascanExecution Spec DataScan execution settings. Structure is documented below.
- Location string
The location where the data scan should reside.
- Data
Profile DatascanSpec Data Profile Spec DataProfileScan related setting. Structure is documented below.
- Data
Quality DatascanSpec Data Quality Spec DataQualityScan related setting. Structure is documented below.
- Description string
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- Display
Name string User friendly display name.
- Labels Dictionary<string, string>
User-defined labels for the scan. A list of key->value pairs.
- Project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- Data
Datascan
Data Args The data source for DataScan. Structure is documented below.
- Data
Scan stringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- Execution
Spec DatascanExecution Spec Args DataScan execution settings. Structure is documented below.
- Location string
The location where the data scan should reside.
- Data
Profile DatascanSpec Data Profile Spec Args DataProfileScan related setting. Structure is documented below.
- Data
Quality DatascanSpec Data Quality Spec Args DataQualityScan related setting. Structure is documented below.
- Description string
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- Display
Name string User friendly display name.
- Labels map[string]string
User-defined labels for the scan. A list of key->value pairs.
- Project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- data
Datascan
Data The data source for DataScan. Structure is documented below.
- data
Scan StringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- execution
Spec DatascanExecution Spec DataScan execution settings. Structure is documented below.
- location String
The location where the data scan should reside.
- data
Profile DatascanSpec Data Profile Spec DataProfileScan related setting. Structure is documented below.
- data
Quality DatascanSpec Data Quality Spec DataQualityScan related setting. Structure is documented below.
- description String
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- display
Name String User friendly display name.
- labels Map<String,String>
User-defined labels for the scan. A list of key->value pairs.
- project String
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- data
Datascan
Data The data source for DataScan. Structure is documented below.
- data
Scan stringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- execution
Spec DatascanExecution Spec DataScan execution settings. Structure is documented below.
- location string
The location where the data scan should reside.
- data
Profile DatascanSpec Data Profile Spec DataProfileScan related setting. Structure is documented below.
- data
Quality DatascanSpec Data Quality Spec DataQualityScan related setting. Structure is documented below.
- description string
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- display
Name string User friendly display name.
- labels {[key: string]: string}
User-defined labels for the scan. A list of key->value pairs.
- project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- data
Datascan
Data Args The data source for DataScan. Structure is documented below.
- data_
scan_ strid DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- execution_
spec DatascanExecution Spec Args DataScan execution settings. Structure is documented below.
- location str
The location where the data scan should reside.
- data_
profile_ Datascanspec Data Profile Spec Args DataProfileScan related setting. Structure is documented below.
- data_
quality_ Datascanspec Data Quality Spec Args DataQualityScan related setting. Structure is documented below.
- description str
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- display_
name str User friendly display name.
- labels Mapping[str, str]
User-defined labels for the scan. A list of key->value pairs.
- project str
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- data Property Map
The data source for DataScan. Structure is documented below.
- data
Scan StringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- execution
Spec Property Map DataScan execution settings. Structure is documented below.
- location String
The location where the data scan should reside.
- data
Profile Property MapSpec DataProfileScan related setting. Structure is documented below.
- data
Quality Property MapSpec DataQualityScan related setting. Structure is documented below.
- description String
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- display
Name String User friendly display name.
- labels Map<String>
User-defined labels for the scan. A list of key->value pairs.
- project String
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
Outputs
All input properties are implicitly available as output properties. Additionally, the Datascan resource produces the following output properties:
- Create
Time string The time when the scan was created.
- Data
Profile List<DatascanResults Data Profile Result> (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- Data
Quality List<DatascanResults Data Quality Result> (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- Execution
Statuses List<DatascanExecution Status> Status of the data scan execution. Structure is documented below.
- Id string
The provider-assigned unique ID for this managed resource.
- Name string
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.
- State string
Current state of the DataScan.
- Type string
The field data type.
- Uid string
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- Update
Time string The time when the scan was last updated.
- Create
Time string The time when the scan was created.
- Data
Profile []DatascanResults Data Profile Result (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- Data
Quality []DatascanResults Data Quality Result (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- Execution
Statuses []DatascanExecution Status Status of the data scan execution. Structure is documented below.
- Id string
The provider-assigned unique ID for this managed resource.
- Name string
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.
- State string
Current state of the DataScan.
- Type string
The field data type.
- Uid string
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- Update
Time string The time when the scan was last updated.
- create
Time String The time when the scan was created.
- data
Profile List<DatascanResults Data Profile Result> (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- data
Quality List<DatascanResults Data Quality Result> (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- execution
Statuses List<DatascanExecution Status> Status of the data scan execution. Structure is documented below.
- id String
The provider-assigned unique ID for this managed resource.
- name String
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.
- state String
Current state of the DataScan.
- type String
The field data type.
- uid String
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- update
Time String The time when the scan was last updated.
- create
Time string The time when the scan was created.
- data
Profile DatascanResults Data Profile Result[] (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- data
Quality DatascanResults Data Quality Result[] (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- execution
Statuses DatascanExecution Status[] Status of the data scan execution. Structure is documented below.
- id string
The provider-assigned unique ID for this managed resource.
- name string
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.
- state string
Current state of the DataScan.
- type string
The field data type.
- uid string
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- update
Time string The time when the scan was last updated.
- create_
time str The time when the scan was created.
- data_
profile_ Sequence[Datascanresults Data Profile Result] (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- data_
quality_ Sequence[Datascanresults Data Quality Result] (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- execution_
statuses Sequence[DatascanExecution Status] Status of the data scan execution. Structure is documented below.
- id str
The provider-assigned unique ID for this managed resource.
- name str
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.
- state str
Current state of the DataScan.
- type str
The field data type.
- uid str
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- update_
time str The time when the scan was last updated.
- create
Time String The time when the scan was created.
- data
Profile List<Property Map>Results (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- data
Quality List<Property Map>Results (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- execution
Statuses List<Property Map> Status of the data scan execution. Structure is documented below.
- id String
The provider-assigned unique ID for this managed resource.
- name String
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.
- state String
Current state of the DataScan.
- type String
The field data type.
- uid String
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- update
Time String The time when the scan was last updated.
Look up Existing Datascan Resource
Get an existing Datascan resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.
public static get(name: string, id: Input<ID>, state?: DatascanState, opts?: CustomResourceOptions): Datascan@staticmethod
def get(resource_name: str,
id: str,
opts: Optional[ResourceOptions] = None,
create_time: Optional[str] = None,
data: Optional[DatascanDataArgs] = None,
data_profile_results: Optional[Sequence[DatascanDataProfileResultArgs]] = None,
data_profile_spec: Optional[DatascanDataProfileSpecArgs] = None,
data_quality_results: Optional[Sequence[DatascanDataQualityResultArgs]] = None,
data_quality_spec: Optional[DatascanDataQualitySpecArgs] = None,
data_scan_id: Optional[str] = None,
description: Optional[str] = None,
display_name: Optional[str] = None,
execution_spec: Optional[DatascanExecutionSpecArgs] = None,
execution_statuses: Optional[Sequence[DatascanExecutionStatusArgs]] = None,
labels: Optional[Mapping[str, str]] = None,
location: Optional[str] = None,
name: Optional[str] = None,
project: Optional[str] = None,
state: Optional[str] = None,
type: Optional[str] = None,
uid: Optional[str] = None,
update_time: Optional[str] = None) -> Datascanfunc GetDatascan(ctx *Context, name string, id IDInput, state *DatascanState, opts ...ResourceOption) (*Datascan, error)public static Datascan Get(string name, Input<string> id, DatascanState? state, CustomResourceOptions? opts = null)public static Datascan get(String name, Output<String> id, DatascanState state, CustomResourceOptions options)Resource lookup is not supported in YAML- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- resource_name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- Create
Time string The time when the scan was created.
- Data
Datascan
Data The data source for DataScan. Structure is documented below.
- Data
Profile List<DatascanResults Data Profile Result> (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- Data
Profile DatascanSpec Data Profile Spec DataProfileScan related setting. Structure is documented below.
- Data
Quality List<DatascanResults Data Quality Result> (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- Data
Quality DatascanSpec Data Quality Spec DataQualityScan related setting. Structure is documented below.
- Data
Scan stringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- Description string
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- Display
Name string User friendly display name.
- Execution
Spec DatascanExecution Spec DataScan execution settings. Structure is documented below.
- Execution
Statuses List<DatascanExecution Status> Status of the data scan execution. Structure is documented below.
- Labels Dictionary<string, string>
User-defined labels for the scan. A list of key->value pairs.
- Location string
The location where the data scan should reside.
- Name string
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.
- Project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- State string
Current state of the DataScan.
- Type string
The field data type.
- Uid string
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- Update
Time string The time when the scan was last updated.
- Create
Time string The time when the scan was created.
- Data
Datascan
Data Args The data source for DataScan. Structure is documented below.
- Data
Profile []DatascanResults Data Profile Result Args (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- Data
Profile DatascanSpec Data Profile Spec Args DataProfileScan related setting. Structure is documented below.
- Data
Quality []DatascanResults Data Quality Result Args (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- Data
Quality DatascanSpec Data Quality Spec Args DataQualityScan related setting. Structure is documented below.
- Data
Scan stringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- Description string
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- Display
Name string User friendly display name.
- Execution
Spec DatascanExecution Spec Args DataScan execution settings. Structure is documented below.
- Execution
Statuses []DatascanExecution Status Args Status of the data scan execution. Structure is documented below.
- Labels map[string]string
User-defined labels for the scan. A list of key->value pairs.
- Location string
The location where the data scan should reside.
- Name string
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.
- Project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- State string
Current state of the DataScan.
- Type string
The field data type.
- Uid string
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- Update
Time string The time when the scan was last updated.
- create
Time String The time when the scan was created.
- data
Datascan
Data The data source for DataScan. Structure is documented below.
- data
Profile List<DatascanResults Data Profile Result> (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- data
Profile DatascanSpec Data Profile Spec DataProfileScan related setting. Structure is documented below.
- data
Quality List<DatascanResults Data Quality Result> (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- data
Quality DatascanSpec Data Quality Spec DataQualityScan related setting. Structure is documented below.
- data
Scan StringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- description String
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- display
Name String User friendly display name.
- execution
Spec DatascanExecution Spec DataScan execution settings. Structure is documented below.
- execution
Statuses List<DatascanExecution Status> Status of the data scan execution. Structure is documented below.
- labels Map<String,String>
User-defined labels for the scan. A list of key->value pairs.
- location String
The location where the data scan should reside.
- name String
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.
- project String
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- state String
Current state of the DataScan.
- type String
The field data type.
- uid String
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- update
Time String The time when the scan was last updated.
- create
Time string The time when the scan was created.
- data
Datascan
Data The data source for DataScan. Structure is documented below.
- data
Profile DatascanResults Data Profile Result[] (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- data
Profile DatascanSpec Data Profile Spec DataProfileScan related setting. Structure is documented below.
- data
Quality DatascanResults Data Quality Result[] (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- data
Quality DatascanSpec Data Quality Spec DataQualityScan related setting. Structure is documented below.
- data
Scan stringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- description string
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- display
Name string User friendly display name.
- execution
Spec DatascanExecution Spec DataScan execution settings. Structure is documented below.
- execution
Statuses DatascanExecution Status[] Status of the data scan execution. Structure is documented below.
- labels {[key: string]: string}
User-defined labels for the scan. A list of key->value pairs.
- location string
The location where the data scan should reside.
- name string
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.
- project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- state string
Current state of the DataScan.
- type string
The field data type.
- uid string
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- update
Time string The time when the scan was last updated.
- create_
time str The time when the scan was created.
- data
Datascan
Data Args The data source for DataScan. Structure is documented below.
- data_
profile_ Sequence[Datascanresults Data Profile Result Args] (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- data_
profile_ Datascanspec Data Profile Spec Args DataProfileScan related setting. Structure is documented below.
- data_
quality_ Sequence[Datascanresults Data Quality Result Args] (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- data_
quality_ Datascanspec Data Quality Spec Args DataQualityScan related setting. Structure is documented below.
- data_
scan_ strid DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- description str
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- display_
name str User friendly display name.
- execution_
spec DatascanExecution Spec Args DataScan execution settings. Structure is documented below.
- execution_
statuses Sequence[DatascanExecution Status Args] Status of the data scan execution. Structure is documented below.
- labels Mapping[str, str]
User-defined labels for the scan. A list of key->value pairs.
- location str
The location where the data scan should reside.
- name str
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.
- project str
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- state str
Current state of the DataScan.
- type str
The field data type.
- uid str
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- update_
time str The time when the scan was last updated.
- create
Time String The time when the scan was created.
- data Property Map
The data source for DataScan. Structure is documented below.
- data
Profile List<Property Map>Results (Deprecated) The result of the data profile scan. Structure is documented below.
data_profile_resultis deprecated and will be removed in a future major release.- data
Profile Property MapSpec DataProfileScan related setting. Structure is documented below.
- data
Quality List<Property Map>Results (Deprecated) The result of the data quality scan. Structure is documented below.
data_quality_resultis deprecated and will be removed in a future major release.- data
Quality Property MapSpec DataQualityScan related setting. Structure is documented below.
- data
Scan StringId DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.
- description String
Description of the scan.
(Optional) Description of the rule. The maximum length is 1,024 characters.
- display
Name String User friendly display name.
- execution
Spec Property Map DataScan execution settings. Structure is documented below.
- execution
Statuses List<Property Map> Status of the data scan execution. Structure is documented below.
- labels Map<String>
User-defined labels for the scan. A list of key->value pairs.
- location String
The location where the data scan should reside.
- name String
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.
- project String
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- state String
Current state of the DataScan.
- type String
The field data type.
- uid String
System generated globally unique ID for the scan. This ID will be different if the scan is deleted and re-created with the same name.
- update
Time String The time when the scan was last updated.
Supporting Types
DatascanData, DatascanDataArgs
- Entity string
The Dataplex entity that represents the data source(e.g. BigQuery table) for Datascan.
- Resource string
The service-qualified full resource name of the cloud resource for a DataScan job to scan against. The field could be: (Cloud Storage bucket for DataDiscoveryScan)BigQuery table of type "TABLE" for DataProfileScan/DataQualityScan.
- Entity string
The Dataplex entity that represents the data source(e.g. BigQuery table) for Datascan.
- Resource string
The service-qualified full resource name of the cloud resource for a DataScan job to scan against. The field could be: (Cloud Storage bucket for DataDiscoveryScan)BigQuery table of type "TABLE" for DataProfileScan/DataQualityScan.
- entity String
The Dataplex entity that represents the data source(e.g. BigQuery table) for Datascan.
- resource String
The service-qualified full resource name of the cloud resource for a DataScan job to scan against. The field could be: (Cloud Storage bucket for DataDiscoveryScan)BigQuery table of type "TABLE" for DataProfileScan/DataQualityScan.
- entity string
The Dataplex entity that represents the data source(e.g. BigQuery table) for Datascan.
- resource string
The service-qualified full resource name of the cloud resource for a DataScan job to scan against. The field could be: (Cloud Storage bucket for DataDiscoveryScan)BigQuery table of type "TABLE" for DataProfileScan/DataQualityScan.
- entity str
The Dataplex entity that represents the data source(e.g. BigQuery table) for Datascan.
- resource str
The service-qualified full resource name of the cloud resource for a DataScan job to scan against. The field could be: (Cloud Storage bucket for DataDiscoveryScan)BigQuery table of type "TABLE" for DataProfileScan/DataQualityScan.
- entity String
The Dataplex entity that represents the data source(e.g. BigQuery table) for Datascan.
- resource String
The service-qualified full resource name of the cloud resource for a DataScan job to scan against. The field could be: (Cloud Storage bucket for DataDiscoveryScan)BigQuery table of type "TABLE" for DataProfileScan/DataQualityScan.
DatascanDataProfileResult, DatascanDataProfileResultArgs
- Profiles
List<Datascan
Data Profile Result Profile> Profile information for the corresponding field. Structure is documented below.
- Row
Count string The count of rows scanned.
- Scanned
Datas List<DatascanData Profile Result Scanned Data> (Output) The data scanned for this result. Structure is documented below.
- Profiles
[]Datascan
Data Profile Result Profile Profile information for the corresponding field. Structure is documented below.
- Row
Count string The count of rows scanned.
- Scanned
Datas []DatascanData Profile Result Scanned Data (Output) The data scanned for this result. Structure is documented below.
- profiles
List<Datascan
Data Profile Result Profile> Profile information for the corresponding field. Structure is documented below.
- row
Count String The count of rows scanned.
- scanned
Datas List<DatascanData Profile Result Scanned Data> (Output) The data scanned for this result. Structure is documented below.
- profiles
Datascan
Data Profile Result Profile[] Profile information for the corresponding field. Structure is documented below.
- row
Count string The count of rows scanned.
- scanned
Datas DatascanData Profile Result Scanned Data[] (Output) The data scanned for this result. Structure is documented below.
- profiles
Sequence[Datascan
Data Profile Result Profile] Profile information for the corresponding field. Structure is documented below.
- row_
count str The count of rows scanned.
- scanned_
datas Sequence[DatascanData Profile Result Scanned Data] (Output) The data scanned for this result. Structure is documented below.
- profiles List<Property Map>
Profile information for the corresponding field. Structure is documented below.
- row
Count String The count of rows scanned.
- scanned
Datas List<Property Map> (Output) The data scanned for this result. Structure is documented below.
DatascanDataProfileResultProfile, DatascanDataProfileResultProfileArgs
- Fields
List<Datascan
Data Profile Result Profile Field> List of fields with structural and profile information for each field. Structure is documented below.
- Fields
[]Datascan
Data Profile Result Profile Field List of fields with structural and profile information for each field. Structure is documented below.
- fields
List<Datascan
Data Profile Result Profile Field> List of fields with structural and profile information for each field. Structure is documented below.
- fields
Datascan
Data Profile Result Profile Field[] List of fields with structural and profile information for each field. Structure is documented below.
- fields
Sequence[Datascan
Data Profile Result Profile Field] List of fields with structural and profile information for each field. Structure is documented below.
- fields List<Property Map>
List of fields with structural and profile information for each field. Structure is documented below.
DatascanDataProfileResultProfileField, DatascanDataProfileResultProfileFieldArgs
- Mode string
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.
- Name string
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.
- Profile
Datascan
Data Profile Result Profile Field Profile Profile information for the corresponding field. Structure is documented below.
- Type string
The field data type.
- Mode string
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.
- Name string
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.
- Profile
Datascan
Data Profile Result Profile Field Profile Profile information for the corresponding field. Structure is documented below.
- Type string
The field data type.
- mode String
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.
- name String
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.
- profile
Datascan
Data Profile Result Profile Field Profile Profile information for the corresponding field. Structure is documented below.
- type String
The field data type.
- mode string
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.
- name string
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.
- profile
Datascan
Data Profile Result Profile Field Profile Profile information for the corresponding field. Structure is documented below.
- type string
The field data type.
- mode str
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.
- name str
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.
- profile
Datascan
Data Profile Result Profile Field Profile Profile information for the corresponding field. Structure is documented below.
- type str
The field data type.
- mode String
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.
- name String
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.
- profile Property Map
Profile information for the corresponding field. Structure is documented below.
- type String
The field data type.
DatascanDataProfileResultProfileFieldProfile, DatascanDataProfileResultProfileFieldProfileArgs
- Distinct
Ratio int Ratio of rows with distinct values against total scanned rows. Not available for complex non-groupable field type RECORD and fields with REPEATABLE mode.
- Double
Profiles List<DatascanData Profile Result Profile Field Profile Double Profile> (Output) Double type field information. Structure is documented below.
- Integer
Profiles List<DatascanData Profile Result Profile Field Profile Integer Profile> (Output) Integer type field information. Structure is documented below.
- Null
Ratio int (Output) Ratio of rows with null value against total scanned rows.
- String
Profiles List<DatascanData Profile Result Profile Field Profile String Profile> (Output) String type field information. Structure is documented below.
- Top
NValues DatascanData Profile Result Profile Field Profile Top NValues The list of top N non-null values and number of times 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. Structure is documented below.
- Distinct
Ratio int Ratio of rows with distinct values against total scanned rows. Not available for complex non-groupable field type RECORD and fields with REPEATABLE mode.
- Double
Profiles []DatascanData Profile Result Profile Field Profile Double Profile (Output) Double type field information. Structure is documented below.
- Integer
Profiles []DatascanData Profile Result Profile Field Profile Integer Profile (Output) Integer type field information. Structure is documented below.
- Null
Ratio int (Output) Ratio of rows with null value against total scanned rows.
- String
Profiles []DatascanData Profile Result Profile Field Profile String Profile (Output) String type field information. Structure is documented below.
- Top
NValues DatascanData Profile Result Profile Field Profile Top NValues The list of top N non-null values and number of times 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. Structure is documented below.
- distinct
Ratio Integer Ratio of rows with distinct values against total scanned rows. Not available for complex non-groupable field type RECORD and fields with REPEATABLE mode.
- double
Profiles List<DatascanData Profile Result Profile Field Profile Double Profile> (Output) Double type field information. Structure is documented below.
- integer
Profiles List<DatascanData Profile Result Profile Field Profile Integer Profile> (Output) Integer type field information. Structure is documented below.
- null
Ratio Integer (Output) Ratio of rows with null value against total scanned rows.
- string
Profiles List<DatascanData Profile Result Profile Field Profile String Profile> (Output) String type field information. Structure is documented below.
- top
NValues DatascanData Profile Result Profile Field Profile Top NValues The list of top N non-null values and number of times 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. Structure is documented below.
- distinct
Ratio number Ratio of rows with distinct values against total scanned rows. Not available for complex non-groupable field type RECORD and fields with REPEATABLE mode.
- double
Profiles DatascanData Profile Result Profile Field Profile Double Profile[] (Output) Double type field information. Structure is documented below.
- integer
Profiles DatascanData Profile Result Profile Field Profile Integer Profile[] (Output) Integer type field information. Structure is documented below.
- null
Ratio number (Output) Ratio of rows with null value against total scanned rows.
- string
Profiles DatascanData Profile Result Profile Field Profile String Profile[] (Output) String type field information. Structure is documented below.
- top
NValues DatascanData Profile Result Profile Field Profile Top NValues The list of top N non-null values and number of times 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. Structure is documented below.
- distinct_
ratio int Ratio of rows with distinct values against total scanned rows. Not available for complex non-groupable field type RECORD and fields with REPEATABLE mode.
- double_
profiles Sequence[DatascanData Profile Result Profile Field Profile Double Profile] (Output) Double type field information. Structure is documented below.
- integer_
profiles Sequence[DatascanData Profile Result Profile Field Profile Integer Profile] (Output) Integer type field information. Structure is documented below.
- null_
ratio int (Output) Ratio of rows with null value against total scanned rows.
- string_
profiles Sequence[DatascanData Profile Result Profile Field Profile String Profile] (Output) String type field information. Structure is documented below.
- top_
n_ Datascanvalues Data Profile Result Profile Field Profile Top NValues The list of top N non-null values and number of times 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. Structure is documented below.
- distinct
Ratio Number Ratio of rows with distinct values against total scanned rows. Not available for complex non-groupable field type RECORD and fields with REPEATABLE mode.
- double
Profiles List<Property Map> (Output) Double type field information. Structure is documented below.
- integer
Profiles List<Property Map> (Output) Integer type field information. Structure is documented below.
- null
Ratio Number (Output) Ratio of rows with null value against total scanned rows.
- string
Profiles List<Property Map> (Output) String type field information. Structure is documented below.
- top
NValues Property Map The list of top N non-null values and number of times 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. Structure is documented below.
DatascanDataProfileResultProfileFieldProfileDoubleProfile, DatascanDataProfileResultProfileFieldProfileDoubleProfileArgs
- Average int
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- Max string
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- Min string
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- Quartiles string
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.
- Standard
Deviation int Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- Average int
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- Max string
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- Min string
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- Quartiles string
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.
- Standard
Deviation int Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- average Integer
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- max String
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- min String
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- quartiles String
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.
- standard
Deviation Integer Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- average number
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- max string
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- min string
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- quartiles string
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.
- standard
Deviation number Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- average int
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- max str
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- min str
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- quartiles str
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.
- standard_
deviation int Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- average Number
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- max String
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- min String
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- quartiles String
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.
- standard
Deviation Number Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
DatascanDataProfileResultProfileFieldProfileIntegerProfile, DatascanDataProfileResultProfileFieldProfileIntegerProfileArgs
- Average int
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- Max string
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- Min string
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- Quartiles string
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.
- Standard
Deviation int Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- Average int
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- Max string
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- Min string
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- Quartiles string
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.
- Standard
Deviation int Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- average Integer
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- max String
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- min String
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- quartiles String
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.
- standard
Deviation Integer Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- average number
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- max string
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- min string
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- quartiles string
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.
- standard
Deviation number Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- average int
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- max str
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- min str
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- quartiles str
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.
- standard_
deviation int Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
- average Number
Average of non-null values in the scanned data. NaN, if the field has a NaN.
- max String
Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
- min String
Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
- quartiles String
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.
- standard
Deviation Number Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
DatascanDataProfileResultProfileFieldProfileStringProfile, DatascanDataProfileResultProfileFieldProfileStringProfileArgs
- Average
Length int Average length of non-null values in the scanned data.
- Max
Length string Maximum length of non-null values in the scanned data.
- Min
Length string Minimum length of non-null values in the scanned data.
- Average
Length int Average length of non-null values in the scanned data.
- Max
Length string Maximum length of non-null values in the scanned data.
- Min
Length string Minimum length of non-null values in the scanned data.
- average
Length Integer Average length of non-null values in the scanned data.
- max
Length String Maximum length of non-null values in the scanned data.
- min
Length String Minimum length of non-null values in the scanned data.
- average
Length number Average length of non-null values in the scanned data.
- max
Length string Maximum length of non-null values in the scanned data.
- min
Length string Minimum length of non-null values in the scanned data.
- average_
length int Average length of non-null values in the scanned data.
- max_
length str Maximum length of non-null values in the scanned data.
- min_
length str Minimum length of non-null values in the scanned data.
- average
Length Number Average length of non-null values in the scanned data.
- max
Length String Maximum length of non-null values in the scanned data.
- min
Length String Minimum length of non-null values in the scanned data.
DatascanDataProfileResultProfileFieldProfileTopNValues, DatascanDataProfileResultProfileFieldProfileTopNValuesArgs
DatascanDataProfileResultScannedData, DatascanDataProfileResultScannedDataArgs
- Incremental
Field DatascanData Profile Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- Incremental
Field DatascanData Profile Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- incremental
Field DatascanData Profile Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- incremental
Field DatascanData Profile Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- incremental_
field DatascanData Profile Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- incremental
Field Property Map The range denoted by values of an incremental field Structure is documented below.
DatascanDataProfileResultScannedDataIncrementalField, DatascanDataProfileResultScannedDataIncrementalFieldArgs
DatascanDataProfileSpec, DatascanDataProfileSpecArgs
- Exclude
Fields DatascanData Profile Spec Exclude Fields The fields to exclude from data profile. If specified, the fields will be excluded from data profile, regardless of
include_fieldsvalue. Structure is documented below.- Include
Fields DatascanData Profile Spec Include Fields 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. Structure is documented below.- Post
Scan DatascanActions Data Profile Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- Row
Filter string 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
- Sampling
Percent double 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_percentis not specified, 0 or 100.
- Exclude
Fields DatascanData Profile Spec Exclude Fields The fields to exclude from data profile. If specified, the fields will be excluded from data profile, regardless of
include_fieldsvalue. Structure is documented below.- Include
Fields DatascanData Profile Spec Include Fields 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. Structure is documented below.- Post
Scan DatascanActions Data Profile Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- Row
Filter string 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
- Sampling
Percent float64 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_percentis not specified, 0 or 100.
- exclude
Fields DatascanData Profile Spec Exclude Fields The fields to exclude from data profile. If specified, the fields will be excluded from data profile, regardless of
include_fieldsvalue. Structure is documented below.- include
Fields DatascanData Profile Spec Include Fields 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. Structure is documented below.- post
Scan DatascanActions Data Profile Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- row
Filter String 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
- sampling
Percent Double 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_percentis not specified, 0 or 100.
- exclude
Fields DatascanData Profile Spec Exclude Fields The fields to exclude from data profile. If specified, the fields will be excluded from data profile, regardless of
include_fieldsvalue. Structure is documented below.- include
Fields DatascanData Profile Spec Include Fields 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. Structure is documented below.- post
Scan DatascanActions Data Profile Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- row
Filter string 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
- sampling
Percent number 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_percentis not specified, 0 or 100.
- exclude_
fields DatascanData Profile Spec Exclude Fields The fields to exclude from data profile. If specified, the fields will be excluded from data profile, regardless of
include_fieldsvalue. Structure is documented below.- include_
fields DatascanData Profile Spec Include Fields 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. Structure is documented below.- post_
scan_ Datascanactions Data Profile Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- row_
filter str 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
- sampling_
percent float 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_percentis not specified, 0 or 100.
- exclude
Fields Property Map The fields to exclude from data profile. If specified, the fields will be excluded from data profile, regardless of
include_fieldsvalue. Structure is documented below.- include
Fields Property Map 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. Structure is documented below.- post
Scan Property MapActions Actions to take upon job completion. Structure is documented below.
- row
Filter String 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
- sampling
Percent Number 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_percentis not specified, 0 or 100.
DatascanDataProfileSpecExcludeFields, DatascanDataProfileSpecExcludeFieldsArgs
- Field
Names List<string> 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'.
- Field
Names []string 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'.
- field
Names List<String> 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'.
- field
Names string[] 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'.
- field_
names Sequence[str] 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'.
- field
Names List<String> 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'.
DatascanDataProfileSpecIncludeFields, DatascanDataProfileSpecIncludeFieldsArgs
- Field
Names List<string> 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'.
- Field
Names []string 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'.
- field
Names List<String> 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'.
- field
Names string[] 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'.
- field_
names Sequence[str] 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'.
- field
Names List<String> 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'.
DatascanDataProfileSpecPostScanActions, DatascanDataProfileSpecPostScanActionsArgs
- Bigquery
Export DatascanData Profile Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- Bigquery
Export DatascanData Profile Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- bigquery
Export DatascanData Profile Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- bigquery
Export DatascanData Profile Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- bigquery_
export DatascanData Profile Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- bigquery
Export Property Map If set, results will be exported to the provided BigQuery table. Structure is documented below.
DatascanDataProfileSpecPostScanActionsBigqueryExport, DatascanDataProfileSpecPostScanActionsBigqueryExportArgs
- Results
Table string The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- Results
Table string The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- results
Table String The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- results
Table string The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- results_
table str The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- results
Table String The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
DatascanDataQualityResult, DatascanDataQualityResultArgs
- Dimensions
List<Datascan
Data Quality Result Dimension> A list of results at the dimension level. Structure is documented below.
- Passed bool
(Output) Whether the rule passed or failed.
- Row
Count string The count of rows scanned.
- Rules
List<Datascan
Data Quality Result Rule> The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- Scanned
Datas List<DatascanData Quality Result Scanned Data> (Output) The data scanned for this result. Structure is documented below.
- Dimensions
[]Datascan
Data Quality Result Dimension A list of results at the dimension level. Structure is documented below.
- Passed bool
(Output) Whether the rule passed or failed.
- Row
Count string The count of rows scanned.
- Rules
[]Datascan
Data Quality Result Rule The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- Scanned
Datas []DatascanData Quality Result Scanned Data (Output) The data scanned for this result. Structure is documented below.
- dimensions
List<Datascan
Data Quality Result Dimension> A list of results at the dimension level. Structure is documented below.
- passed Boolean
(Output) Whether the rule passed or failed.
- row
Count String The count of rows scanned.
- rules
List<Datascan
Data Quality Result Rule> The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- scanned
Datas List<DatascanData Quality Result Scanned Data> (Output) The data scanned for this result. Structure is documented below.
- dimensions
Datascan
Data Quality Result Dimension[] A list of results at the dimension level. Structure is documented below.
- passed boolean
(Output) Whether the rule passed or failed.
- row
Count string The count of rows scanned.
- rules
Datascan
Data Quality Result Rule[] The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- scanned
Datas DatascanData Quality Result Scanned Data[] (Output) The data scanned for this result. Structure is documented below.
- dimensions
Sequence[Datascan
Data Quality Result Dimension] A list of results at the dimension level. Structure is documented below.
- passed bool
(Output) Whether the rule passed or failed.
- row_
count str The count of rows scanned.
- rules
Sequence[Datascan
Data Quality Result Rule] The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- scanned_
datas Sequence[DatascanData Quality Result Scanned Data] (Output) The data scanned for this result. Structure is documented below.
- dimensions List<Property Map>
A list of results at the dimension level. Structure is documented below.
- passed Boolean
(Output) Whether the rule passed or failed.
- row
Count String The count of rows scanned.
- rules List<Property Map>
The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- scanned
Datas List<Property Map> (Output) The data scanned for this result. Structure is documented below.
DatascanDataQualityResultDimension, DatascanDataQualityResultDimensionArgs
- Passed bool
(Output) Whether the rule passed or failed.
- Passed bool
(Output) Whether the rule passed or failed.
- passed Boolean
(Output) Whether the rule passed or failed.
- passed boolean
(Output) Whether the rule passed or failed.
- passed bool
(Output) Whether the rule passed or failed.
- passed Boolean
(Output) Whether the rule passed or failed.
DatascanDataQualityResultRule, DatascanDataQualityResultRuleArgs
- Evaluated
Count string (Output) The number of rows a rule was evaluated against. This field is only valid for ColumnMap 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 evaluatedCount, by setting ignore_nulls = true.
- Failing
Rows stringQuery (Output) The query to find rows that did not pass this rule. Only applies to ColumnMap and RowCondition rules.
- Null
Count string (Output) The number of rows with null values in the specified column.
- Pass
Ratio int (Output) The ratio of passedCount / evaluatedCount. This field is only valid for ColumnMap type rules.
- Passed bool
(Output) Whether the rule passed or failed.
- Passed
Count string (Output) The number of rows which passed a rule evaluation. This field is only valid for ColumnMap type rules.
- Rules
List<Datascan
Data Quality Result Rule Rule> (Output) The rule specified in the DataQualitySpec, as is. Structure is documented below.
- Evaluated
Count string (Output) The number of rows a rule was evaluated against. This field is only valid for ColumnMap 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 evaluatedCount, by setting ignore_nulls = true.
- Failing
Rows stringQuery (Output) The query to find rows that did not pass this rule. Only applies to ColumnMap and RowCondition rules.
- Null
Count string (Output) The number of rows with null values in the specified column.
- Pass
Ratio int (Output) The ratio of passedCount / evaluatedCount. This field is only valid for ColumnMap type rules.
- Passed bool
(Output) Whether the rule passed or failed.
- Passed
Count string (Output) The number of rows which passed a rule evaluation. This field is only valid for ColumnMap type rules.
- Rules
[]Datascan
Data Quality Result Rule Rule (Output) The rule specified in the DataQualitySpec, as is. Structure is documented below.
- evaluated
Count String (Output) The number of rows a rule was evaluated against. This field is only valid for ColumnMap 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 evaluatedCount, by setting ignore_nulls = true.
- failing
Rows StringQuery (Output) The query to find rows that did not pass this rule. Only applies to ColumnMap and RowCondition rules.
- null
Count String (Output) The number of rows with null values in the specified column.
- pass
Ratio Integer (Output) The ratio of passedCount / evaluatedCount. This field is only valid for ColumnMap type rules.
- passed Boolean
(Output) Whether the rule passed or failed.
- passed
Count String (Output) The number of rows which passed a rule evaluation. This field is only valid for ColumnMap type rules.
- rules
List<Datascan
Data Quality Result Rule Rule> (Output) The rule specified in the DataQualitySpec, as is. Structure is documented below.
- evaluated
Count string (Output) The number of rows a rule was evaluated against. This field is only valid for ColumnMap 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 evaluatedCount, by setting ignore_nulls = true.
- failing
Rows stringQuery (Output) The query to find rows that did not pass this rule. Only applies to ColumnMap and RowCondition rules.
- null
Count string (Output) The number of rows with null values in the specified column.
- pass
Ratio number (Output) The ratio of passedCount / evaluatedCount. This field is only valid for ColumnMap type rules.
- passed boolean
(Output) Whether the rule passed or failed.
- passed
Count string (Output) The number of rows which passed a rule evaluation. This field is only valid for ColumnMap type rules.
- rules
Datascan
Data Quality Result Rule Rule[] (Output) The rule specified in the DataQualitySpec, as is. Structure is documented below.
- evaluated_
count str (Output) The number of rows a rule was evaluated against. This field is only valid for ColumnMap 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 evaluatedCount, by setting ignore_nulls = true.
- failing_
rows_ strquery (Output) The query to find rows that did not pass this rule. Only applies to ColumnMap and RowCondition rules.
- null_
count str (Output) The number of rows with null values in the specified column.
- pass_
ratio int (Output) The ratio of passedCount / evaluatedCount. This field is only valid for ColumnMap type rules.
- passed bool
(Output) Whether the rule passed or failed.
- passed_
count str (Output) The number of rows which passed a rule evaluation. This field is only valid for ColumnMap type rules.
- rules
Sequence[Datascan
Data Quality Result Rule Rule] (Output) The rule specified in the DataQualitySpec, as is. Structure is documented below.
- evaluated
Count String (Output) The number of rows a rule was evaluated against. This field is only valid for ColumnMap 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 evaluatedCount, by setting ignore_nulls = true.
- failing
Rows StringQuery (Output) The query to find rows that did not pass this rule. Only applies to ColumnMap and RowCondition rules.
- null
Count String (Output) The number of rows with null values in the specified column.
- pass
Ratio Number (Output) The ratio of passedCount / evaluatedCount. This field is only valid for ColumnMap type rules.
- passed Boolean
(Output) Whether the rule passed or failed.
- passed
Count String (Output) The number of rows which passed a rule evaluation. This field is only valid for ColumnMap type rules.
- rules List<Property Map>
(Output) The rule specified in the DataQualitySpec, as is. Structure is documented below.
DatascanDataQualityResultRuleRule, DatascanDataQualityResultRuleRuleArgs
- Column string
The unnested column which this rule is evaluated against.
- Dimension string
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- Ignore
Null bool Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- Non
Null List<DatascanExpectations Data Quality Result Rule Rule Non Null Expectation> ColumnMap rule which evaluates whether each column value is null.
- Range
Expectations List<DatascanData Quality Result Rule Rule Range Expectation> ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- Regex
Expectations List<DatascanData Quality Result Rule Rule Regex Expectation> ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- Row
Condition List<DatascanExpectations Data Quality Result Rule Rule Row Condition Expectation> Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- Set
Expectations List<DatascanData Quality Result Rule Rule Set Expectation> ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- Statistic
Range List<DatascanExpectations Data Quality Result Rule Rule Statistic Range Expectation> ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- Table
Condition List<DatascanExpectations Data Quality Result Rule Rule Table Condition Expectation> Table rule which evaluates whether the provided expression is true. Structure is documented below.
- Threshold int
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).
- Uniqueness
Expectations List<DatascanData Quality Result Rule Rule Uniqueness Expectation> Row-level rule which evaluates whether each column value is unique.
- Column string
The unnested column which this rule is evaluated against.
- Dimension string
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- Ignore
Null bool Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- Non
Null []DatascanExpectations Data Quality Result Rule Rule Non Null Expectation ColumnMap rule which evaluates whether each column value is null.
- Range
Expectations []DatascanData Quality Result Rule Rule Range Expectation ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- Regex
Expectations []DatascanData Quality Result Rule Rule Regex Expectation ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- Row
Condition []DatascanExpectations Data Quality Result Rule Rule Row Condition Expectation Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- Set
Expectations []DatascanData Quality Result Rule Rule Set Expectation ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- Statistic
Range []DatascanExpectations Data Quality Result Rule Rule Statistic Range Expectation ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- Table
Condition []DatascanExpectations Data Quality Result Rule Rule Table Condition Expectation Table rule which evaluates whether the provided expression is true. Structure is documented below.
- Threshold int
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).
- Uniqueness
Expectations []DatascanData Quality Result Rule Rule Uniqueness Expectation Row-level rule which evaluates whether each column value is unique.
- column String
The unnested column which this rule is evaluated against.
- dimension String
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- ignore
Null Boolean Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- non
Null List<DatascanExpectations Data Quality Result Rule Rule Non Null Expectation> ColumnMap rule which evaluates whether each column value is null.
- range
Expectations List<DatascanData Quality Result Rule Rule Range Expectation> ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- regex
Expectations List<DatascanData Quality Result Rule Rule Regex Expectation> ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- row
Condition List<DatascanExpectations Data Quality Result Rule Rule Row Condition Expectation> Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- set
Expectations List<DatascanData Quality Result Rule Rule Set Expectation> ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- statistic
Range List<DatascanExpectations Data Quality Result Rule Rule Statistic Range Expectation> ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- table
Condition List<DatascanExpectations Data Quality Result Rule Rule Table Condition Expectation> Table rule which evaluates whether the provided expression is true. Structure is documented below.
- threshold Integer
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).
- uniqueness
Expectations List<DatascanData Quality Result Rule Rule Uniqueness Expectation> Row-level rule which evaluates whether each column value is unique.
- column string
The unnested column which this rule is evaluated against.
- dimension string
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- ignore
Null boolean Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- non
Null DatascanExpectations Data Quality Result Rule Rule Non Null Expectation[] ColumnMap rule which evaluates whether each column value is null.
- range
Expectations DatascanData Quality Result Rule Rule Range Expectation[] ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- regex
Expectations DatascanData Quality Result Rule Rule Regex Expectation[] ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- row
Condition DatascanExpectations Data Quality Result Rule Rule Row Condition Expectation[] Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- set
Expectations DatascanData Quality Result Rule Rule Set Expectation[] ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- statistic
Range DatascanExpectations Data Quality Result Rule Rule Statistic Range Expectation[] ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- table
Condition DatascanExpectations Data Quality Result Rule Rule Table Condition Expectation[] Table rule which evaluates whether the provided expression is true. Structure is documented below.
- threshold number
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).
- uniqueness
Expectations DatascanData Quality Result Rule Rule Uniqueness Expectation[] Row-level rule which evaluates whether each column value is unique.
- column str
The unnested column which this rule is evaluated against.
- dimension str
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- ignore_
null bool Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- non_
null_ Sequence[Datascanexpectations Data Quality Result Rule Rule Non Null Expectation] ColumnMap rule which evaluates whether each column value is null.
- range_
expectations Sequence[DatascanData Quality Result Rule Rule Range Expectation] ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- regex_
expectations Sequence[DatascanData Quality Result Rule Rule Regex Expectation] ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- row_
condition_ Sequence[Datascanexpectations Data Quality Result Rule Rule Row Condition Expectation] Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- set_
expectations Sequence[DatascanData Quality Result Rule Rule Set Expectation] ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- statistic_
range_ Sequence[Datascanexpectations Data Quality Result Rule Rule Statistic Range Expectation] ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- table_
condition_ Sequence[Datascanexpectations Data Quality Result Rule Rule Table Condition Expectation] Table rule which evaluates whether the provided expression is true. Structure is documented below.
- threshold int
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).
- uniqueness_
expectations Sequence[DatascanData Quality Result Rule Rule Uniqueness Expectation] Row-level rule which evaluates whether each column value is unique.
- column String
The unnested column which this rule is evaluated against.
- dimension String
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- ignore
Null Boolean Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- non
Null List<Property Map>Expectations ColumnMap rule which evaluates whether each column value is null.
- range
Expectations List<Property Map> ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- regex
Expectations List<Property Map> ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- row
Condition List<Property Map>Expectations Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- set
Expectations List<Property Map> ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- statistic
Range List<Property Map>Expectations ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- table
Condition List<Property Map>Expectations Table rule which evaluates whether the provided expression is true. Structure is documented below.
- threshold Number
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).
- uniqueness
Expectations List<Property Map> Row-level rule which evaluates whether each column value is unique.
DatascanDataQualityResultRuleRuleRangeExpectation, DatascanDataQualityResultRuleRuleRangeExpectationArgs
- Max
Value string The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Min
Value string The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Strict
Max boolEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- Strict
Min boolEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- Max
Value string The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Min
Value string The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Strict
Max boolEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- Strict
Min boolEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value String The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value String The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max BooleanEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min BooleanEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value string The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value string The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max booleanEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min booleanEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max_
value str The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min_
value str The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict_
max_ boolenabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict_
min_ boolenabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value String The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value String The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max BooleanEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min BooleanEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
DatascanDataQualityResultRuleRuleRegexExpectation, DatascanDataQualityResultRuleRuleRegexExpectationArgs
- Regex string
A regular expression the column value is expected to match.
- Regex string
A regular expression the column value is expected to match.
- regex String
A regular expression the column value is expected to match.
- regex string
A regular expression the column value is expected to match.
- regex str
A regular expression the column value is expected to match.
- regex String
A regular expression the column value is expected to match.
DatascanDataQualityResultRuleRuleRowConditionExpectation, DatascanDataQualityResultRuleRuleRowConditionExpectationArgs
- Sql
Expression string The SQL expression.
- Sql
Expression string The SQL expression.
- sql
Expression String The SQL expression.
- sql
Expression string The SQL expression.
- sql_
expression str The SQL expression.
- sql
Expression String The SQL expression.
DatascanDataQualityResultRuleRuleSetExpectation, DatascanDataQualityResultRuleRuleSetExpectationArgs
- Values List<string>
Expected values for the column value.
- Values []string
Expected values for the column value.
- values List<String>
Expected values for the column value.
- values string[]
Expected values for the column value.
- values Sequence[str]
Expected values for the column value.
- values List<String>
Expected values for the column value.
DatascanDataQualityResultRuleRuleStatisticRangeExpectation, DatascanDataQualityResultRuleRuleStatisticRangeExpectationArgs
- Max
Value string The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Min
Value string The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Statistic string
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- Strict
Max boolEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- Strict
Min boolEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- Max
Value string The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Min
Value string The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Statistic string
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- Strict
Max boolEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- Strict
Min boolEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value String The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value String The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- statistic String
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- strict
Max BooleanEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min BooleanEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value string The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value string The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- statistic string
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- strict
Max booleanEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min booleanEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max_
value str The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min_
value str The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- statistic str
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- strict_
max_ boolenabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict_
min_ boolenabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value String The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value String The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- statistic String
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- strict
Max BooleanEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min BooleanEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
DatascanDataQualityResultRuleRuleTableConditionExpectation, DatascanDataQualityResultRuleRuleTableConditionExpectationArgs
- Sql
Expression string The SQL expression.
- Sql
Expression string The SQL expression.
- sql
Expression String The SQL expression.
- sql
Expression string The SQL expression.
- sql_
expression str The SQL expression.
- sql
Expression String The SQL expression.
DatascanDataQualityResultScannedData, DatascanDataQualityResultScannedDataArgs
- Incremental
Field DatascanData Quality Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- Incremental
Field DatascanData Quality Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- incremental
Field DatascanData Quality Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- incremental
Field DatascanData Quality Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- incremental_
field DatascanData Quality Result Scanned Data Incremental Field The range denoted by values of an incremental field Structure is documented below.
- incremental
Field Property Map The range denoted by values of an incremental field Structure is documented below.
DatascanDataQualityResultScannedDataIncrementalField, DatascanDataQualityResultScannedDataIncrementalFieldArgs
DatascanDataQualitySpec, DatascanDataQualitySpecArgs
- Post
Scan DatascanActions Data Quality Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- Row
Filter string 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
- Rules
List<Datascan
Data Quality Spec Rule> The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- Sampling
Percent double 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_percentis not specified, 0 or 100.
- Post
Scan DatascanActions Data Quality Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- Row
Filter string 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
- Rules
[]Datascan
Data Quality Spec Rule The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- Sampling
Percent float64 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_percentis not specified, 0 or 100.
- post
Scan DatascanActions Data Quality Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- row
Filter String 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
- rules
List<Datascan
Data Quality Spec Rule> The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- sampling
Percent Double 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_percentis not specified, 0 or 100.
- post
Scan DatascanActions Data Quality Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- row
Filter string 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
- rules
Datascan
Data Quality Spec Rule[] The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- sampling
Percent number 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_percentis not specified, 0 or 100.
- post_
scan_ Datascanactions Data Quality Spec Post Scan Actions Actions to take upon job completion. Structure is documented below.
- row_
filter str 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
- rules
Sequence[Datascan
Data Quality Spec Rule] The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- sampling_
percent float 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_percentis not specified, 0 or 100.
- post
Scan Property MapActions Actions to take upon job completion. Structure is documented below.
- row
Filter String 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
- rules List<Property Map>
The list of rules to evaluate against a data source. At least one rule is required. Structure is documented below.
- sampling
Percent Number 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_percentis not specified, 0 or 100.
DatascanDataQualitySpecPostScanActions, DatascanDataQualitySpecPostScanActionsArgs
- Bigquery
Export DatascanData Quality Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- Bigquery
Export DatascanData Quality Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- bigquery
Export DatascanData Quality Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- bigquery
Export DatascanData Quality Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- bigquery_
export DatascanData Quality Spec Post Scan Actions Bigquery Export If set, results will be exported to the provided BigQuery table. Structure is documented below.
- bigquery
Export Property Map If set, results will be exported to the provided BigQuery table. Structure is documented below.
DatascanDataQualitySpecPostScanActionsBigqueryExport, DatascanDataQualitySpecPostScanActionsBigqueryExportArgs
- Results
Table string The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- Results
Table string The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- results
Table String The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- results
Table string The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- results_
table str The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
- results
Table String The BigQuery table to export DataProfileScan results to. Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
DatascanDataQualitySpecRule, DatascanDataQualitySpecRuleArgs
- Dimension string
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- Column string
The unnested column which this rule is evaluated against.
- Description string
Description of the rule. The maximum length is 1,024 characters.
- Ignore
Null bool Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- Name string
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.
- Non
Null DatascanExpectation Data Quality Spec Rule Non Null Expectation ColumnMap rule which evaluates whether each column value is null.
- Range
Expectation DatascanData Quality Spec Rule Range Expectation ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- Regex
Expectation DatascanData Quality Spec Rule Regex Expectation ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- Row
Condition DatascanExpectation Data Quality Spec Rule Row Condition Expectation Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- Set
Expectation DatascanData Quality Spec Rule Set Expectation ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- Statistic
Range DatascanExpectation Data Quality Spec Rule Statistic Range Expectation ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- Table
Condition DatascanExpectation Data Quality Spec Rule Table Condition Expectation Table rule which evaluates whether the provided expression is true. Structure is documented below.
- Threshold double
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).
- Uniqueness
Expectation DatascanData Quality Spec Rule Uniqueness Expectation Row-level rule which evaluates whether each column value is unique.
- Dimension string
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- Column string
The unnested column which this rule is evaluated against.
- Description string
Description of the rule. The maximum length is 1,024 characters.
- Ignore
Null bool Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- Name string
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.
- Non
Null DatascanExpectation Data Quality Spec Rule Non Null Expectation ColumnMap rule which evaluates whether each column value is null.
- Range
Expectation DatascanData Quality Spec Rule Range Expectation ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- Regex
Expectation DatascanData Quality Spec Rule Regex Expectation ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- Row
Condition DatascanExpectation Data Quality Spec Rule Row Condition Expectation Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- Set
Expectation DatascanData Quality Spec Rule Set Expectation ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- Statistic
Range DatascanExpectation Data Quality Spec Rule Statistic Range Expectation ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- Table
Condition DatascanExpectation Data Quality Spec Rule Table Condition Expectation Table rule which evaluates whether the provided expression is true. Structure is documented below.
- Threshold float64
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).
- Uniqueness
Expectation DatascanData Quality Spec Rule Uniqueness Expectation Row-level rule which evaluates whether each column value is unique.
- dimension String
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- column String
The unnested column which this rule is evaluated against.
- description String
Description of the rule. The maximum length is 1,024 characters.
- ignore
Null Boolean Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- name String
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.
- non
Null DatascanExpectation Data Quality Spec Rule Non Null Expectation ColumnMap rule which evaluates whether each column value is null.
- range
Expectation DatascanData Quality Spec Rule Range Expectation ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- regex
Expectation DatascanData Quality Spec Rule Regex Expectation ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- row
Condition DatascanExpectation Data Quality Spec Rule Row Condition Expectation Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- set
Expectation DatascanData Quality Spec Rule Set Expectation ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- statistic
Range DatascanExpectation Data Quality Spec Rule Statistic Range Expectation ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- table
Condition DatascanExpectation Data Quality Spec Rule Table Condition Expectation Table rule which evaluates whether the provided expression is true. Structure is documented below.
- threshold Double
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).
- uniqueness
Expectation DatascanData Quality Spec Rule Uniqueness Expectation Row-level rule which evaluates whether each column value is unique.
- dimension string
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- column string
The unnested column which this rule is evaluated against.
- description string
Description of the rule. The maximum length is 1,024 characters.
- ignore
Null boolean Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- name string
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.
- non
Null DatascanExpectation Data Quality Spec Rule Non Null Expectation ColumnMap rule which evaluates whether each column value is null.
- range
Expectation DatascanData Quality Spec Rule Range Expectation ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- regex
Expectation DatascanData Quality Spec Rule Regex Expectation ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- row
Condition DatascanExpectation Data Quality Spec Rule Row Condition Expectation Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- set
Expectation DatascanData Quality Spec Rule Set Expectation ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- statistic
Range DatascanExpectation Data Quality Spec Rule Statistic Range Expectation ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- table
Condition DatascanExpectation Data Quality Spec Rule Table Condition Expectation Table rule which evaluates whether the provided expression is true. Structure is documented below.
- threshold number
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).
- uniqueness
Expectation DatascanData Quality Spec Rule Uniqueness Expectation Row-level rule which evaluates whether each column value is unique.
- dimension str
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- column str
The unnested column which this rule is evaluated against.
- description str
Description of the rule. The maximum length is 1,024 characters.
- ignore_
null bool Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- name str
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.
- non_
null_ Datascanexpectation Data Quality Spec Rule Non Null Expectation ColumnMap rule which evaluates whether each column value is null.
- range_
expectation DatascanData Quality Spec Rule Range Expectation ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- regex_
expectation DatascanData Quality Spec Rule Regex Expectation ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- row_
condition_ Datascanexpectation Data Quality Spec Rule Row Condition Expectation Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- set_
expectation DatascanData Quality Spec Rule Set Expectation ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- statistic_
range_ Datascanexpectation Data Quality Spec Rule Statistic Range Expectation ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- table_
condition_ Datascanexpectation Data Quality Spec Rule Table Condition Expectation Table rule which evaluates whether the provided expression is true. Structure is documented below.
- threshold float
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).
- uniqueness_
expectation DatascanData Quality Spec Rule Uniqueness Expectation Row-level rule which evaluates whether each column value is unique.
- dimension String
The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]
- column String
The unnested column which this rule is evaluated against.
- description String
Description of the rule. The maximum length is 1,024 characters.
- ignore
Null Boolean Rows with null values will automatically fail a rule, unless ignoreNull is true. In that case, such null rows are trivially considered passing. Only applicable to ColumnMap rules.
- name String
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.
- non
Null Property MapExpectation ColumnMap rule which evaluates whether each column value is null.
- range
Expectation Property Map ColumnMap rule which evaluates whether each column value lies between a specified range. Structure is documented below.
- regex
Expectation Property Map ColumnMap rule which evaluates whether each column value matches a specified regex. Structure is documented below.
- row
Condition Property MapExpectation Table rule which evaluates whether each row passes the specified condition. Structure is documented below.
- set
Expectation Property Map ColumnMap rule which evaluates whether each column value is contained by a specified set. Structure is documented below.
- statistic
Range Property MapExpectation ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range. Structure is documented below.
- table
Condition Property MapExpectation Table rule which evaluates whether the provided expression is true. Structure is documented below.
- threshold Number
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).
- uniqueness
Expectation Property Map Row-level rule which evaluates whether each column value is unique.
DatascanDataQualitySpecRuleRangeExpectation, DatascanDataQualitySpecRuleRangeExpectationArgs
- Max
Value string The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Min
Value string The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Strict
Max boolEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- Strict
Min boolEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- Max
Value string The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Min
Value string The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Strict
Max boolEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- Strict
Min boolEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value String The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value String The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max BooleanEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min BooleanEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value string The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value string The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max booleanEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min booleanEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max_
value str The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min_
value str The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict_
max_ boolenabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict_
min_ boolenabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- max
Value String The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value String The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max BooleanEnabled Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min BooleanEnabled Whether each value needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
DatascanDataQualitySpecRuleRegexExpectation, DatascanDataQualitySpecRuleRegexExpectationArgs
- Regex string
A regular expression the column value is expected to match.
- Regex string
A regular expression the column value is expected to match.
- regex String
A regular expression the column value is expected to match.
- regex string
A regular expression the column value is expected to match.
- regex str
A regular expression the column value is expected to match.
- regex String
A regular expression the column value is expected to match.
DatascanDataQualitySpecRuleRowConditionExpectation, DatascanDataQualitySpecRuleRowConditionExpectationArgs
- Sql
Expression string The SQL expression.
- Sql
Expression string The SQL expression.
- sql
Expression String The SQL expression.
- sql
Expression string The SQL expression.
- sql_
expression str The SQL expression.
- sql
Expression String The SQL expression.
DatascanDataQualitySpecRuleSetExpectation, DatascanDataQualitySpecRuleSetExpectationArgs
- Values List<string>
Expected values for the column value.
- Values []string
Expected values for the column value.
- values List<String>
Expected values for the column value.
- values string[]
Expected values for the column value.
- values Sequence[str]
Expected values for the column value.
- values List<String>
Expected values for the column value.
DatascanDataQualitySpecRuleStatisticRangeExpectation, DatascanDataQualitySpecRuleStatisticRangeExpectationArgs
- Statistic string
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- Max
Value string The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Min
Value string The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Strict
Max boolEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- Strict
Min boolEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- Statistic string
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- Max
Value string The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Min
Value string The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- Strict
Max boolEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- Strict
Min boolEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- statistic String
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- max
Value String The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value String The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max BooleanEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min BooleanEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- statistic string
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- max
Value string The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value string The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max booleanEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min booleanEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- statistic str
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- max_
value str The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min_
value str The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict_
max_ boolenabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict_
min_ boolenabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
- statistic String
column statistics. Possible values are:
STATISTIC_UNDEFINED,MEAN,MIN,MAX.- max
Value String The maximum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- min
Value String The minimum column statistic value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.
- strict
Max BooleanEnabled Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed. Only relevant if a maxValue has been defined. Default = false.
- strict
Min BooleanEnabled Whether column statistic needs to be strictly greater than ('>') the minimum, or if equality is allowed. Only relevant if a minValue has been defined. Default = false.
DatascanDataQualitySpecRuleTableConditionExpectation, DatascanDataQualitySpecRuleTableConditionExpectationArgs
- Sql
Expression string The SQL expression.
- Sql
Expression string The SQL expression.
- sql
Expression String The SQL expression.
- sql
Expression string The SQL expression.
- sql_
expression str The SQL expression.
- sql
Expression String The SQL expression.
DatascanExecutionSpec, DatascanExecutionSpecArgs
- Trigger
Datascan
Execution Spec Trigger Spec related to how often and when a scan should be triggered. Structure is documented below.
- Field string
The unnested field (of type Date or Timestamp) that contains values which monotonically increase over time. If not specified, a data scan will run for all data in the table.
- Trigger
Datascan
Execution Spec Trigger Spec related to how often and when a scan should be triggered. Structure is documented below.
- Field string
The unnested field (of type Date or Timestamp) that contains values which monotonically increase over time. If not specified, a data scan will run for all data in the table.
- trigger
Datascan
Execution Spec Trigger Spec related to how often and when a scan should be triggered. Structure is documented below.
- field String
The unnested field (of type Date or Timestamp) that contains values which monotonically increase over time. If not specified, a data scan will run for all data in the table.
- trigger
Datascan
Execution Spec Trigger Spec related to how often and when a scan should be triggered. Structure is documented below.
- field string
The unnested field (of type Date or Timestamp) that contains values which monotonically increase over time. If not specified, a data scan will run for all data in the table.
- trigger
Datascan
Execution Spec Trigger Spec related to how often and when a scan should be triggered. Structure is documented below.
- field str
The unnested field (of type Date or Timestamp) that contains values which monotonically increase over time. If not specified, a data scan will run for all data in the table.
- trigger Property Map
Spec related to how often and when a scan should be triggered. Structure is documented below.
- field String
The unnested field (of type Date or Timestamp) that contains values which monotonically increase over time. If not specified, a data scan will run for all data in the table.
DatascanExecutionSpecTrigger, DatascanExecutionSpecTriggerArgs
- On
Demand DatascanExecution Spec Trigger On Demand The scan runs once via dataScans.run API.
- Schedule
Datascan
Execution Spec Trigger Schedule The scan is scheduled to run periodically. Structure is documented below.
- On
Demand DatascanExecution Spec Trigger On Demand The scan runs once via dataScans.run API.
- Schedule
Datascan
Execution Spec Trigger Schedule The scan is scheduled to run periodically. Structure is documented below.
- on
Demand DatascanExecution Spec Trigger On Demand The scan runs once via dataScans.run API.
- schedule
Datascan
Execution Spec Trigger Schedule The scan is scheduled to run periodically. Structure is documented below.
- on
Demand DatascanExecution Spec Trigger On Demand The scan runs once via dataScans.run API.
- schedule
Datascan
Execution Spec Trigger Schedule The scan is scheduled to run periodically. Structure is documented below.
- on_
demand DatascanExecution Spec Trigger On Demand The scan runs once via dataScans.run API.
- schedule
Datascan
Execution Spec Trigger Schedule The scan is scheduled to run periodically. Structure is documented below.
- on
Demand Property Map The scan runs once via dataScans.run API.
- schedule Property Map
The scan is scheduled to run periodically. Structure is documented below.
DatascanExecutionSpecTriggerSchedule, DatascanExecutionSpecTriggerScheduleArgs
- Cron string
Cron schedule for running scans periodically. This field is required for Schedule scans.
- Cron string
Cron schedule for running scans periodically. This field is required for Schedule scans.
- cron String
Cron schedule for running scans periodically. This field is required for Schedule scans.
- cron string
Cron schedule for running scans periodically. This field is required for Schedule scans.
- cron str
Cron schedule for running scans periodically. This field is required for Schedule scans.
- cron String
Cron schedule for running scans periodically. This field is required for Schedule scans.
DatascanExecutionStatus, DatascanExecutionStatusArgs
- Latest
Job stringEnd Time (Output) The time when the latest DataScanJob started.
- Latest
Job stringStart Time (Output) The time when the latest DataScanJob ended.
- Latest
Job stringEnd Time (Output) The time when the latest DataScanJob started.
- Latest
Job stringStart Time (Output) The time when the latest DataScanJob ended.
- latest
Job StringEnd Time (Output) The time when the latest DataScanJob started.
- latest
Job StringStart Time (Output) The time when the latest DataScanJob ended.
- latest
Job stringEnd Time (Output) The time when the latest DataScanJob started.
- latest
Job stringStart Time (Output) The time when the latest DataScanJob ended.
- latest_
job_ strend_ time (Output) The time when the latest DataScanJob started.
- latest_
job_ strstart_ time (Output) The time when the latest DataScanJob ended.
- latest
Job StringEnd Time (Output) The time when the latest DataScanJob started.
- latest
Job StringStart Time (Output) The time when the latest DataScanJob ended.
Import
Datascan can be imported using any of these accepted formats
$ pulumi import gcp:dataplex/datascan:Datascan default projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}
$ pulumi import gcp:dataplex/datascan:Datascan default {{project}}/{{location}}/{{data_scan_id}}
$ pulumi import gcp:dataplex/datascan:Datascan default {{location}}/{{data_scan_id}}
$ pulumi import gcp:dataplex/datascan:Datascan default {{data_scan_id}}
Package Details
- Repository
- Google Cloud (GCP) Classic pulumi/pulumi-gcp
- License
- Apache-2.0
- Notes
This Pulumi package is based on the
google-betaTerraform Provider.