v6.2.0/website/docs/r/dataplex_datascan.html.markdown - terraform-provider-google-beta - Git at Google

 ---
 # ----------------------------------------------------------------------------
 #
 #     ***     AUTO GENERATED CODE    ***    Type: MMv1     ***
 #
 # ----------------------------------------------------------------------------
 #
 #     This file is automatically generated by Magic Modules and manual
 #     changes will be clobbered when the file is regenerated.
 #
 #     Please read more about how to change this file in
 #     .github/CONTRIBUTING.md.
 #
 # ----------------------------------------------------------------------------
 subcategory: "Dataplex"
 description: |-
   Represents a user-visible job which provides the insights for the related data source.
 ---

 # google_dataplex_datascan

 Represents a user-visible job which provides the insights for the related data source.


 To get more information about Datascan, see:

 * [API documentation](https://cloud.google.com/dataplex/docs/reference/rest)
 * How-to Guides
     * [Official Documentation](https://cloud.google.com/dataplex/docs)

 ## Example Usage - Dataplex Datascan Basic Profile


 ```hcl
 resource "google_dataplex_datascan" "basic_profile" {
   location     = "us-central1"
   data_scan_id = "dataprofile-basic"

   data {
 	  resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"
   }

   execution_spec {
     trigger {
       on_demand {}
     }
   }

 data_profile_spec {}

   project = "my-project-name"
 }
 ```
 ## Example Usage - Dataplex Datascan Full Profile


 ```hcl
 resource "google_dataplex_datascan" "full_profile" {
   location     = "us-central1"
   display_name = "Full Datascan Profile"
   data_scan_id = "dataprofile-full"
   description  = "Example resource - Full Datascan Profile"
   labels = {
     author = "billing"
   }

   data {
     resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"
   }

   execution_spec {
     trigger {
       schedule {
         cron = "TZ=America/New_York 1 1 * * *"
       }
     }
   }

   data_profile_spec {
     sampling_percent = 80
     row_filter = "word_count > 10"
     include_fields {
       field_names = ["word_count"]
     }
     exclude_fields {
       field_names = ["property_type"]
     }
     post_scan_actions {
       bigquery_export {
         results_table = "//bigquery.googleapis.com/projects/my-project-name/datasets/dataplex_dataset/tables/profile_export"
       }
     }
   }

   project = "my-project-name"

   depends_on = [
     google_bigquery_dataset.source
   ]
 }

 resource "google_bigquery_dataset" "source" {
   dataset_id                  = "dataplex_dataset"
   friendly_name               = "test"
   description                 = "This is a test description"
   location                    = "US"
   delete_contents_on_destroy = true
 }
 ```
 ## Example Usage - Dataplex Datascan Basic Quality


 ```hcl
 resource "google_dataplex_datascan" "basic_quality" {
   location     = "us-central1"
   data_scan_id = "dataquality-basic"

   data {
     resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"
   }

   execution_spec {
     trigger {
       on_demand {}
     }
   }

   data_quality_spec {
     rules {
       dimension = "VALIDITY"
       name = "rule1"
       description = "rule 1 for validity dimension"
       table_condition_expectation {
         sql_expression = "COUNT(*) > 0"
       }
     }
   }

   project = "my-project-name"
 }
 ```
 ## Example Usage - Dataplex Datascan Full Quality


 ```hcl
 resource "google_dataplex_datascan" "full_quality" {
   location = "us-central1"
   display_name = "Full Datascan Quality"
   data_scan_id = "dataquality-full"
   description = "Example resource - Full Datascan Quality"
   labels = {
     author = "billing"
   }

   data {
     resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/austin_bikeshare/tables/bikeshare_stations"
   }

   execution_spec {
     trigger {
       schedule {
         cron = "TZ=America/New_York 1 1 * * *"
       }
     }
     field = "modified_date"
   }

   data_quality_spec {
     sampling_percent = 5
     row_filter = "station_id > 1000"
     rules {
       column = "address"
       dimension = "VALIDITY"
       threshold = 0.99
       non_null_expectation {}
     }

     rules {
       column = "council_district"
       dimension = "VALIDITY"
       ignore_null = true
       threshold = 0.9
       range_expectation {
         min_value = 1
         max_value = 10
         strict_min_enabled = true
         strict_max_enabled = false
       }
     }

     rules {
       column = "power_type"
       dimension = "VALIDITY"
       ignore_null = false
       regex_expectation {
         regex = ".*solar.*"
       }
     }

     rules {
       column = "property_type"
       dimension = "VALIDITY"
       ignore_null = false
       set_expectation {
         values = ["sidewalk", "parkland"]
       }
     }


     rules {
       column = "address"
       dimension = "UNIQUENESS"
       uniqueness_expectation {}
     }

     rules {
       column = "number_of_docks"
       dimension = "VALIDITY"
       statistic_range_expectation {
         statistic = "MEAN"
         min_value = 5
         max_value = 15
         strict_min_enabled = true
         strict_max_enabled = true
       }
     }

     rules {
       column = "footprint_length"
       dimension = "VALIDITY"
       row_condition_expectation {
         sql_expression = "footprint_length > 0 AND footprint_length <= 10"
       }
     }

     rules {
       dimension = "VALIDITY"
       table_condition_expectation {
         sql_expression = "COUNT(*) > 0"
       }
     }

     rules {
       dimension = "VALIDITY"
       sql_assertion {
         sql_statement = "select * from bigquery-public-data.austin_bikeshare.bikeshare_stations where station_id is null"
       }
     }
   }


   project = "my-project-name"
 }
 ```

 ## Argument Reference

 The following arguments are supported:


 * `data` -
   (Required)
   The data source for DataScan.
   Structure is [documented below](#nested_data).

 * `execution_spec` -
   (Required)
   DataScan execution settings.
   Structure is [documented below](#nested_execution_spec).

 * `location` -
   (Required)
   The location where the data scan should reside.

 * `data_scan_id` -
   (Required)
   DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.


 <a name="nested_data"></a>The `data` block supports:

 * `entity` -
   (Optional)
   The Dataplex entity that represents the data source(e.g. BigQuery table) for Datascan.

 * `resource` -
   (Optional)
   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.

 <a name="nested_execution_spec"></a>The `execution_spec` block supports:

 * `trigger` -
   (Required)
   Spec related to how often and when a scan should be triggered.
   Structure is [documented below](#nested_trigger).

 * `field` -
   (Optional)
   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.


 <a name="nested_trigger"></a>The `trigger` block supports:

 * `on_demand` -
   (Optional)
   The scan runs once via dataScans.run API.

 * `schedule` -
   (Optional)
   The scan is scheduled to run periodically.
   Structure is [documented below](#nested_schedule).


 <a name="nested_schedule"></a>The `schedule` block supports:

 * `cron` -
   (Required)
   Cron schedule for running scans periodically. This field is required for Schedule scans.

 - - -


 * `description` -
   (Optional)
   Description of the scan.

 * `display_name` -
   (Optional)
   User friendly display name.

 * `labels` -
   (Optional)
   User-defined labels for the scan. A list of key->value pairs.

   **Note**: This field is non-authoritative, and will only manage the labels present in your configuration.
   Please refer to the field `effective_labels` for all of the labels present on the resource.

 * `data_quality_spec` -
   (Optional)
   DataQualityScan related setting.
   Structure is [documented below](#nested_data_quality_spec).

 * `data_profile_spec` -
   (Optional)
   DataProfileScan related setting.
   Structure is [documented below](#nested_data_profile_spec).

 * `project` - (Optional) The ID of the project in which the resource belongs.
     If it is not provided, the provider project is used.


 <a name="nested_data_quality_spec"></a>The `data_quality_spec` block supports:

 * `sampling_percent` -
   (Optional)
   The percentage of the records to be selected from the dataset for DataScan.
   Value can range between 0.0 and 100.0 with up to 3 significant decimal digits.
   Sampling is not applied if `sampling_percent` is not specified, 0 or 100.

 * `row_filter` -
   (Optional)
   A filter applied to all rows in a single DataScan job. The filter needs to be a valid SQL expression for a WHERE clause in BigQuery standard SQL syntax. Example: col1 >= 0 AND col2 < 10

 * `post_scan_actions` -
   (Optional)
   Actions to take upon job completion.
   Structure is [documented below](#nested_post_scan_actions).

 * `rules` -
   (Optional)
   The list of rules to evaluate against a data source. At least one rule is required.
   Structure is [documented below](#nested_rules).


 <a name="nested_post_scan_actions"></a>The `post_scan_actions` block supports:

 * `bigquery_export` -
   (Optional)
   If set, results will be exported to the provided BigQuery table.
   Structure is [documented below](#nested_bigquery_export).


 <a name="nested_bigquery_export"></a>The `bigquery_export` block supports:

 * `results_table` -
   (Optional)
   The BigQuery table to export DataQualityScan results to.
   Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID

 <a name="nested_rules"></a>The `rules` block supports:

 * `column` -
   (Optional)
   The unnested column which this rule is evaluated against.

 * `ignore_null` -
   (Optional)
   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.

 * `dimension` -
   (Required)
   The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]

 * `threshold` -
   (Optional)
   The minimum ratio of passing_rows / total_rows required to pass this rule, with a range of [0.0, 1.0]. 0 indicates default value (i.e. 1.0).

 * `name` -
   (Optional)
   A mutable name for the rule.
   The name must contain only letters (a-z, A-Z), numbers (0-9), or hyphens (-).
   The maximum length is 63 characters.
   Must start with a letter.
   Must end with a number or a letter.

 * `description` -
   (Optional)
   Description of the rule.
   The maximum length is 1,024 characters.

 * `range_expectation` -
   (Optional)
   ColumnMap rule which evaluates whether each column value lies between a specified range.
   Structure is [documented below](#nested_range_expectation).

 * `non_null_expectation` -
   (Optional)
   ColumnMap rule which evaluates whether each column value is null.

 * `set_expectation` -
   (Optional)
   ColumnMap rule which evaluates whether each column value is contained by a specified set.
   Structure is [documented below](#nested_set_expectation).

 * `regex_expectation` -
   (Optional)
   ColumnMap rule which evaluates whether each column value matches a specified regex.
   Structure is [documented below](#nested_regex_expectation).

 * `uniqueness_expectation` -
   (Optional)
   Row-level rule which evaluates whether each column value is unique.

 * `statistic_range_expectation` -
   (Optional)
   ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range.
   Structure is [documented below](#nested_statistic_range_expectation).

 * `row_condition_expectation` -
   (Optional)
   Table rule which evaluates whether each row passes the specified condition.
   Structure is [documented below](#nested_row_condition_expectation).

 * `table_condition_expectation` -
   (Optional)
   Table rule which evaluates whether the provided expression is true.
   Structure is [documented below](#nested_table_condition_expectation).

 * `sql_assertion` -
   (Optional)
   Table rule which evaluates whether any row matches invalid state.
   Structure is [documented below](#nested_sql_assertion).


 <a name="nested_range_expectation"></a>The `range_expectation` block supports:

 * `min_value` -
   (Optional)
   The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.

 * `max_value` -
   (Optional)
   The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.

 * `strict_min_enabled` -
   (Optional)
   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.

 * `strict_max_enabled` -
   (Optional)
   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.

 <a name="nested_set_expectation"></a>The `set_expectation` block supports:

 * `values` -
   (Required)
   Expected values for the column value.

 <a name="nested_regex_expectation"></a>The `regex_expectation` block supports:

 * `regex` -
   (Required)
   A regular expression the column value is expected to match.

 <a name="nested_statistic_range_expectation"></a>The `statistic_range_expectation` block supports:

 * `statistic` -
   (Required)
   column statistics.
   Possible values are: `STATISTIC_UNDEFINED`, `MEAN`, `MIN`, `MAX`.

 * `min_value` -
   (Optional)
   The minimum column statistic value allowed for a row to pass this validation.
   At least one of minValue and maxValue need to be provided.

 * `max_value` -
   (Optional)
   The maximum column statistic value allowed for a row to pass this validation.
   At least one of minValue and maxValue need to be provided.

 * `strict_min_enabled` -
   (Optional)
   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.

 * `strict_max_enabled` -
   (Optional)
   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.

 <a name="nested_row_condition_expectation"></a>The `row_condition_expectation` block supports:

 * `sql_expression` -
   (Required)
   The SQL expression.

 <a name="nested_table_condition_expectation"></a>The `table_condition_expectation` block supports:

 * `sql_expression` -
   (Required)
   The SQL expression.

 <a name="nested_sql_assertion"></a>The `sql_assertion` block supports:

 * `sql_statement` -
   (Required)
   The SQL statement.

 <a name="nested_data_profile_spec"></a>The `data_profile_spec` block supports:

 * `sampling_percent` -
   (Optional)
   The percentage of the records to be selected from the dataset for DataScan.
   Value can range between 0.0 and 100.0 with up to 3 significant decimal digits.
   Sampling is not applied if `sampling_percent` is not specified, 0 or 100.

 * `row_filter` -
   (Optional)
   A filter applied to all rows in a single DataScan job. The filter needs to be a valid SQL expression for a WHERE clause in BigQuery standard SQL syntax. Example: col1 >= 0 AND col2 < 10

 * `post_scan_actions` -
   (Optional)
   Actions to take upon job completion.
   Structure is [documented below](#nested_post_scan_actions).

 * `include_fields` -
   (Optional)
   The fields to include in data profile.
   If not specified, all fields at the time of profile scan job execution are included, except for ones listed in `exclude_fields`.
   Structure is [documented below](#nested_include_fields).

 * `exclude_fields` -
   (Optional)
   The fields to exclude from data profile.
   If specified, the fields will be excluded from data profile, regardless of `include_fields` value.
   Structure is [documented below](#nested_exclude_fields).


 <a name="nested_post_scan_actions"></a>The `post_scan_actions` block supports:

 * `bigquery_export` -
   (Optional)
   If set, results will be exported to the provided BigQuery table.
   Structure is [documented below](#nested_bigquery_export).


 <a name="nested_bigquery_export"></a>The `bigquery_export` block supports:

 * `results_table` -
   (Optional)
   The BigQuery table to export DataProfileScan results to.
   Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID

 <a name="nested_include_fields"></a>The `include_fields` block supports:

 * `field_names` -
   (Optional)
   Expected input is a list of fully qualified names of fields as in the schema.
   Only top-level field names for nested fields are supported.
   For instance, if 'x' is of nested field type, listing 'x' is supported but 'x.y.z' is not supported. Here 'y' and 'y.z' are nested fields of 'x'.

 <a name="nested_exclude_fields"></a>The `exclude_fields` block supports:

 * `field_names` -
   (Optional)
   Expected input is a list of fully qualified names of fields as in the schema.
   Only top-level field names for nested fields are supported.
   For instance, if 'x' is of nested field type, listing 'x' is supported but 'x.y.z' is not supported. Here 'y' and 'y.z' are nested fields of 'x'.

 ## Attributes Reference

 In addition to the arguments listed above, the following computed attributes are exported:

 * `id` - an identifier for the resource with format `projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}`

 * `name` -
   The relative resource name of the scan, of the form: projects/{project}/locations/{locationId}/dataScans/{datascan_id}, where project refers to a project_id or project_number and locationId refers to a GCP region.

 * `uid` -
   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.

 * `state` -
   Current state of the DataScan.

 * `create_time` -
   The time when the scan was created.

 * `update_time` -
   The time when the scan was last updated.

 * `execution_status` -
   Status of the data scan execution.
   Structure is [documented below](#nested_execution_status).

 * `type` -
   The type of DataScan.

 * `terraform_labels` -
   The combination of labels configured directly on the resource
    and default labels configured on the provider.

 * `effective_labels` -
   All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Terraform, other clients and services.


 <a name="nested_execution_status"></a>The `execution_status` block contains:

 * `latest_job_end_time` -
   (Output)
   The time when the latest DataScanJob started.

 * `latest_job_start_time` -
   (Output)
   The time when the latest DataScanJob ended.

 ## Timeouts

 This resource provides the following
 [Timeouts](https://developer.hashicorp.com/terraform/plugin/sdkv2/resources/retries-and-customizable-timeouts) configuration options:

 - `create` - Default is 5 minutes.
 - `update` - Default is 5 minutes.
 - `delete` - Default is 5 minutes.

 ## Import


 Datascan can be imported using any of these accepted formats:

 * `projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}`
 * `{{project}}/{{location}}/{{data_scan_id}}`
 * `{{location}}/{{data_scan_id}}`
 * `{{data_scan_id}}`


 In Terraform v1.5.0 and later, use an [`import` block](https://developer.hashicorp.com/terraform/language/import) to import Datascan using one of the formats above. For example:

 ```tf
 import {
   id = "projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}"
   to = google_dataplex_datascan.default
 }
 ```

 When using the [`terraform import` command](https://developer.hashicorp.com/terraform/cli/commands/import), Datascan can be imported using one of the formats above. For example:

 ```
 $ terraform import google_dataplex_datascan.default projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}
 $ terraform import google_dataplex_datascan.default {{project}}/{{location}}/{{data_scan_id}}
 $ terraform import google_dataplex_datascan.default {{location}}/{{data_scan_id}}
 $ terraform import google_dataplex_datascan.default {{data_scan_id}}
 ```

 ## User Project Overrides

 This resource supports [User Project Overrides](https://registry.terraform.io/providers/hashicorp/google/latest/docs/guides/provider_reference#user_project_override).
	---
	# ----------------------------------------------------------------------------
	#
	# * AUTO GENERATED CODE * Type: MMv1 ***
	#
	# ----------------------------------------------------------------------------
	#
	# This file is automatically generated by Magic Modules and manual
	# changes will be clobbered when the file is regenerated.
	#
	# Please read more about how to change this file in
	# .github/CONTRIBUTING.md.
	#
	# ----------------------------------------------------------------------------
	subcategory: "Dataplex"
	description: \|-
	Represents a user-visible job which provides the insights for the related data source.
	---

	# google_dataplex_datascan

	Represents a user-visible job which provides the insights for the related data source.


	To get more information about Datascan, see:

	* [API documentation](https://cloud.google.com/dataplex/docs/reference/rest)
	* How-to Guides
	* [Official Documentation](https://cloud.google.com/dataplex/docs)

	## Example Usage - Dataplex Datascan Basic Profile


	```hcl
	resource "google_dataplex_datascan" "basic_profile" {
	location = "us-central1"
	data_scan_id = "dataprofile-basic"

	data {
	resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"
	}

	execution_spec {
	trigger {
	on_demand {}
	}
	}

	data_profile_spec {}

	project = "my-project-name"
	}
	```
	## Example Usage - Dataplex Datascan Full Profile


	```hcl
	resource "google_dataplex_datascan" "full_profile" {
	location = "us-central1"
	display_name = "Full Datascan Profile"
	data_scan_id = "dataprofile-full"
	description = "Example resource - Full Datascan Profile"
	labels = {
	author = "billing"
	}

	data {
	resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"
	}

	execution_spec {
	trigger {
	schedule {
	cron = "TZ=America/New_York 1 1 * * *"
	}
	}
	}

	data_profile_spec {
	sampling_percent = 80
	row_filter = "word_count > 10"
	include_fields {
	field_names = ["word_count"]
	}
	exclude_fields {
	field_names = ["property_type"]
	}
	post_scan_actions {
	bigquery_export {
	results_table = "//bigquery.googleapis.com/projects/my-project-name/datasets/dataplex_dataset/tables/profile_export"
	}
	}
	}

	project = "my-project-name"

	depends_on = [
	google_bigquery_dataset.source
	]
	}

	resource "google_bigquery_dataset" "source" {
	dataset_id = "dataplex_dataset"
	friendly_name = "test"
	description = "This is a test description"
	location = "US"
	delete_contents_on_destroy = true
	}
	```
	## Example Usage - Dataplex Datascan Basic Quality


	```hcl
	resource "google_dataplex_datascan" "basic_quality" {
	location = "us-central1"
	data_scan_id = "dataquality-basic"

	data {
	resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/samples/tables/shakespeare"
	}

	execution_spec {
	trigger {
	on_demand {}
	}
	}

	data_quality_spec {
	rules {
	dimension = "VALIDITY"
	name = "rule1"
	description = "rule 1 for validity dimension"
	table_condition_expectation {
	sql_expression = "COUNT(*) > 0"
	}
	}
	}

	project = "my-project-name"
	}
	```
	## Example Usage - Dataplex Datascan Full Quality


	```hcl
	resource "google_dataplex_datascan" "full_quality" {
	location = "us-central1"
	display_name = "Full Datascan Quality"
	data_scan_id = "dataquality-full"
	description = "Example resource - Full Datascan Quality"
	labels = {
	author = "billing"
	}

	data {
	resource = "//bigquery.googleapis.com/projects/bigquery-public-data/datasets/austin_bikeshare/tables/bikeshare_stations"
	}

	execution_spec {
	trigger {
	schedule {
	cron = "TZ=America/New_York 1 1 * * *"
	}
	}
	field = "modified_date"
	}

	data_quality_spec {
	sampling_percent = 5
	row_filter = "station_id > 1000"
	rules {
	column = "address"
	dimension = "VALIDITY"
	threshold = 0.99
	non_null_expectation {}
	}

	rules {
	column = "council_district"
	dimension = "VALIDITY"
	ignore_null = true
	threshold = 0.9
	range_expectation {
	min_value = 1
	max_value = 10
	strict_min_enabled = true
	strict_max_enabled = false
	}
	}

	rules {
	column = "power_type"
	dimension = "VALIDITY"
	ignore_null = false
	regex_expectation {
	regex = ".solar."
	}
	}

	rules {
	column = "property_type"
	dimension = "VALIDITY"
	ignore_null = false
	set_expectation {
	values = ["sidewalk", "parkland"]
	}
	}


	rules {
	column = "address"
	dimension = "UNIQUENESS"
	uniqueness_expectation {}
	}

	rules {
	column = "number_of_docks"
	dimension = "VALIDITY"
	statistic_range_expectation {
	statistic = "MEAN"
	min_value = 5
	max_value = 15
	strict_min_enabled = true
	strict_max_enabled = true
	}
	}

	rules {
	column = "footprint_length"
	dimension = "VALIDITY"
	row_condition_expectation {
	sql_expression = "footprint_length > 0 AND footprint_length <= 10"
	}
	}

	rules {
	dimension = "VALIDITY"
	table_condition_expectation {
	sql_expression = "COUNT(*) > 0"
	}
	}

	rules {
	dimension = "VALIDITY"
	sql_assertion {
	sql_statement = "select * from bigquery-public-data.austin_bikeshare.bikeshare_stations where station_id is null"
	}
	}
	}


	project = "my-project-name"
	}
	```

	## Argument Reference

	The following arguments are supported:


	* `data` -
	(Required)
	The data source for DataScan.
	Structure is [documented below](#nested_data).

	* `execution_spec` -
	(Required)
	DataScan execution settings.
	Structure is [documented below](#nested_execution_spec).

	* `location` -
	(Required)
	The location where the data scan should reside.

	* `data_scan_id` -
	(Required)
	DataScan identifier. Must contain only lowercase letters, numbers and hyphens. Must start with a letter. Must end with a number or a letter.


	<a name="nested_data"></a>The `data` block supports:

	* `entity` -
	(Optional)
	The Dataplex entity that represents the data source(e.g. BigQuery table) for Datascan.

	* `resource` -
	(Optional)
	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.

	<a name="nested_execution_spec"></a>The `execution_spec` block supports:

	* `trigger` -
	(Required)
	Spec related to how often and when a scan should be triggered.
	Structure is [documented below](#nested_trigger).

	* `field` -
	(Optional)
	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.


	<a name="nested_trigger"></a>The `trigger` block supports:

	* `on_demand` -
	(Optional)
	The scan runs once via dataScans.run API.

	* `schedule` -
	(Optional)
	The scan is scheduled to run periodically.
	Structure is [documented below](#nested_schedule).


	<a name="nested_schedule"></a>The `schedule` block supports:

	* `cron` -
	(Required)
	Cron schedule for running scans periodically. This field is required for Schedule scans.

	- - -


	* `description` -
	(Optional)
	Description of the scan.

	* `display_name` -
	(Optional)
	User friendly display name.

	* `labels` -
	(Optional)
	User-defined labels for the scan. A list of key->value pairs.

	Note: This field is non-authoritative, and will only manage the labels present in your configuration.
	Please refer to the field `effective_labels` for all of the labels present on the resource.

	* `data_quality_spec` -
	(Optional)
	DataQualityScan related setting.
	Structure is [documented below](#nested_data_quality_spec).

	* `data_profile_spec` -
	(Optional)
	DataProfileScan related setting.
	Structure is [documented below](#nested_data_profile_spec).

	* `project` - (Optional) The ID of the project in which the resource belongs.
	If it is not provided, the provider project is used.


	<a name="nested_data_quality_spec"></a>The `data_quality_spec` block supports:

	* `sampling_percent` -
	(Optional)
	The percentage of the records to be selected from the dataset for DataScan.
	Value can range between 0.0 and 100.0 with up to 3 significant decimal digits.
	Sampling is not applied if `sampling_percent` is not specified, 0 or 100.

	* `row_filter` -
	(Optional)
	A filter applied to all rows in a single DataScan job. The filter needs to be a valid SQL expression for a WHERE clause in BigQuery standard SQL syntax. Example: col1 >= 0 AND col2 < 10

	* `post_scan_actions` -
	(Optional)
	Actions to take upon job completion.
	Structure is [documented below](#nested_post_scan_actions).

	* `rules` -
	(Optional)
	The list of rules to evaluate against a data source. At least one rule is required.
	Structure is [documented below](#nested_rules).


	<a name="nested_post_scan_actions"></a>The `post_scan_actions` block supports:

	* `bigquery_export` -
	(Optional)
	If set, results will be exported to the provided BigQuery table.
	Structure is [documented below](#nested_bigquery_export).


	<a name="nested_bigquery_export"></a>The `bigquery_export` block supports:

	* `results_table` -
	(Optional)
	The BigQuery table to export DataQualityScan results to.
	Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID

	<a name="nested_rules"></a>The `rules` block supports:

	* `column` -
	(Optional)
	The unnested column which this rule is evaluated against.

	* `ignore_null` -
	(Optional)
	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.

	* `dimension` -
	(Required)
	The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are ["COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"]

	* `threshold` -
	(Optional)
	The minimum ratio of passing_rows / total_rows required to pass this rule, with a range of [0.0, 1.0]. 0 indicates default value (i.e. 1.0).

	* `name` -
	(Optional)
	A mutable name for the rule.
	The name must contain only letters (a-z, A-Z), numbers (0-9), or hyphens (-).
	The maximum length is 63 characters.
	Must start with a letter.
	Must end with a number or a letter.

	* `description` -
	(Optional)
	Description of the rule.
	The maximum length is 1,024 characters.

	* `range_expectation` -
	(Optional)
	ColumnMap rule which evaluates whether each column value lies between a specified range.
	Structure is [documented below](#nested_range_expectation).

	* `non_null_expectation` -
	(Optional)
	ColumnMap rule which evaluates whether each column value is null.

	* `set_expectation` -
	(Optional)
	ColumnMap rule which evaluates whether each column value is contained by a specified set.
	Structure is [documented below](#nested_set_expectation).

	* `regex_expectation` -
	(Optional)
	ColumnMap rule which evaluates whether each column value matches a specified regex.
	Structure is [documented below](#nested_regex_expectation).

	* `uniqueness_expectation` -
	(Optional)
	Row-level rule which evaluates whether each column value is unique.

	* `statistic_range_expectation` -
	(Optional)
	ColumnAggregate rule which evaluates whether the column aggregate statistic lies between a specified range.
	Structure is [documented below](#nested_statistic_range_expectation).

	* `row_condition_expectation` -
	(Optional)
	Table rule which evaluates whether each row passes the specified condition.
	Structure is [documented below](#nested_row_condition_expectation).

	* `table_condition_expectation` -
	(Optional)
	Table rule which evaluates whether the provided expression is true.
	Structure is [documented below](#nested_table_condition_expectation).

	* `sql_assertion` -
	(Optional)
	Table rule which evaluates whether any row matches invalid state.
	Structure is [documented below](#nested_sql_assertion).


	<a name="nested_range_expectation"></a>The `range_expectation` block supports:

	* `min_value` -
	(Optional)
	The minimum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.

	* `max_value` -
	(Optional)
	The maximum column value allowed for a row to pass this validation. At least one of minValue and maxValue need to be provided.

	* `strict_min_enabled` -
	(Optional)
	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.

	* `strict_max_enabled` -
	(Optional)
	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.

	<a name="nested_set_expectation"></a>The `set_expectation` block supports:

	* `values` -
	(Required)
	Expected values for the column value.

	<a name="nested_regex_expectation"></a>The `regex_expectation` block supports:

	* `regex` -
	(Required)
	A regular expression the column value is expected to match.

	<a name="nested_statistic_range_expectation"></a>The `statistic_range_expectation` block supports:

	* `statistic` -
	(Required)
	column statistics.
	Possible values are: `STATISTIC_UNDEFINED`, `MEAN`, `MIN`, `MAX`.

	* `min_value` -
	(Optional)
	The minimum column statistic value allowed for a row to pass this validation.
	At least one of minValue and maxValue need to be provided.

	* `max_value` -
	(Optional)
	The maximum column statistic value allowed for a row to pass this validation.
	At least one of minValue and maxValue need to be provided.

	* `strict_min_enabled` -
	(Optional)
	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.

	* `strict_max_enabled` -
	(Optional)
	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.

	<a name="nested_row_condition_expectation"></a>The `row_condition_expectation` block supports:

	* `sql_expression` -
	(Required)
	The SQL expression.

	<a name="nested_table_condition_expectation"></a>The `table_condition_expectation` block supports:

	* `sql_expression` -
	(Required)
	The SQL expression.

	<a name="nested_sql_assertion"></a>The `sql_assertion` block supports:

	* `sql_statement` -
	(Required)
	The SQL statement.

	<a name="nested_data_profile_spec"></a>The `data_profile_spec` block supports:

	* `sampling_percent` -
	(Optional)
	The percentage of the records to be selected from the dataset for DataScan.
	Value can range between 0.0 and 100.0 with up to 3 significant decimal digits.
	Sampling is not applied if `sampling_percent` is not specified, 0 or 100.

	* `row_filter` -
	(Optional)
	A filter applied to all rows in a single DataScan job. The filter needs to be a valid SQL expression for a WHERE clause in BigQuery standard SQL syntax. Example: col1 >= 0 AND col2 < 10

	* `post_scan_actions` -
	(Optional)
	Actions to take upon job completion.
	Structure is [documented below](#nested_post_scan_actions).

	* `include_fields` -
	(Optional)
	The fields to include in data profile.
	If not specified, all fields at the time of profile scan job execution are included, except for ones listed in `exclude_fields`.
	Structure is [documented below](#nested_include_fields).

	* `exclude_fields` -
	(Optional)
	The fields to exclude from data profile.
	If specified, the fields will be excluded from data profile, regardless of `include_fields` value.
	Structure is [documented below](#nested_exclude_fields).


	<a name="nested_post_scan_actions"></a>The `post_scan_actions` block supports:

	* `bigquery_export` -
	(Optional)
	If set, results will be exported to the provided BigQuery table.
	Structure is [documented below](#nested_bigquery_export).


	<a name="nested_bigquery_export"></a>The `bigquery_export` block supports:

	* `results_table` -
	(Optional)
	The BigQuery table to export DataProfileScan results to.
	Format://bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID

	<a name="nested_include_fields"></a>The `include_fields` block supports:

	* `field_names` -
	(Optional)
	Expected input is a list of fully qualified names of fields as in the schema.
	Only top-level field names for nested fields are supported.
	For instance, if 'x' is of nested field type, listing 'x' is supported but 'x.y.z' is not supported. Here 'y' and 'y.z' are nested fields of 'x'.

	<a name="nested_exclude_fields"></a>The `exclude_fields` block supports:

	* `field_names` -
	(Optional)
	Expected input is a list of fully qualified names of fields as in the schema.
	Only top-level field names for nested fields are supported.
	For instance, if 'x' is of nested field type, listing 'x' is supported but 'x.y.z' is not supported. Here 'y' and 'y.z' are nested fields of 'x'.

	## Attributes Reference

	In addition to the arguments listed above, the following computed attributes are exported:

	* `id` - an identifier for the resource with format `projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}`

	* `name` -
	The relative resource name of the scan, of the form: projects/{project}/locations/{locationId}/dataScans/{datascan_id}, where project refers to a project_id or project_number and locationId refers to a GCP region.

	* `uid` -
	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.

	* `state` -
	Current state of the DataScan.

	* `create_time` -
	The time when the scan was created.

	* `update_time` -
	The time when the scan was last updated.

	* `execution_status` -
	Status of the data scan execution.
	Structure is [documented below](#nested_execution_status).

	* `type` -
	The type of DataScan.

	* `terraform_labels` -
	The combination of labels configured directly on the resource
	and default labels configured on the provider.

	* `effective_labels` -
	All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Terraform, other clients and services.


	<a name="nested_execution_status"></a>The `execution_status` block contains:

	* `latest_job_end_time` -
	(Output)
	The time when the latest DataScanJob started.

	* `latest_job_start_time` -
	(Output)
	The time when the latest DataScanJob ended.

	## Timeouts

	This resource provides the following
	[Timeouts](https://developer.hashicorp.com/terraform/plugin/sdkv2/resources/retries-and-customizable-timeouts) configuration options:

	- `create` - Default is 5 minutes.
	- `update` - Default is 5 minutes.
	- `delete` - Default is 5 minutes.

	## Import


	Datascan can be imported using any of these accepted formats:

	* `projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}`
	* `{{project}}/{{location}}/{{data_scan_id}}`
	* `{{location}}/{{data_scan_id}}`
	* `{{data_scan_id}}`


	In Terraform v1.5.0 and later, use an [`import` block](https://developer.hashicorp.com/terraform/language/import) to import Datascan using one of the formats above. For example:

	```tf
	import {
	id = "projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}"
	to = google_dataplex_datascan.default
	}
	```

	When using the [`terraform import` command](https://developer.hashicorp.com/terraform/cli/commands/import), Datascan can be imported using one of the formats above. For example:

	```
	$ terraform import google_dataplex_datascan.default projects/{{project}}/locations/{{location}}/dataScans/{{data_scan_id}}
	$ terraform import google_dataplex_datascan.default {{project}}/{{location}}/{{data_scan_id}}
	$ terraform import google_dataplex_datascan.default {{location}}/{{data_scan_id}}
	$ terraform import google_dataplex_datascan.default {{data_scan_id}}
	```

	## User Project Overrides

	This resource supports [User Project Overrides](https://registry.terraform.io/providers/hashicorp/google/latest/docs/guides/provider_reference#user_project_override).