Class: Google::Cloud::Dataplex::V1::DataProfileSpec

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/dataplex/v1/data_profile.rb

Overview

DataProfileScan related setting.

Defined Under Namespace

Modules: Mode Classes: PostScanActions, SelectedFields

Instance Attribute Summary collapse

Instance Attribute Details

#catalog_publishing_enabled ⇒ ::Boolean

Returns Optional. If set, the latest DataScan job result will be published as Dataplex Universal Catalog metadata.

Returns:

  • (::Boolean) —

    Optional. If set, the latest DataScan job result will be published as Dataplex Universal Catalog metadata.



62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
# File 'proto_docs/google/cloud/dataplex/v1/data_profile.rb', line 62

class DataProfileSpec
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The configuration of post scan actions of DataProfileScan job.
  # @!attribute [rw] bigquery_export
  #   @return [::Google::Cloud::Dataplex::V1::DataProfileSpec::PostScanActions::BigQueryExport]
  #     Optional. If set, results will be exported to the provided BigQuery
  #     table.
  class PostScanActions
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The configuration of BigQuery export post scan action.
    # @!attribute [rw] results_table
    #   @return [::String]
    #     Optional. The BigQuery table to export DataProfileScan results to.
    #     Format:
    #     //bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
    class BigQueryExport
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # The specification for fields to include or exclude in data profile scan.
  # @!attribute [rw] field_names
  #   @return [::Array<::String>]
  #     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'.
  class SelectedFields
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Defines the execution mode for the profile scan.
  module Mode
    # Default value. This value is unused.
    MODE_UNSPECIFIED = 0

    # Performs standard profiling. The behavior is controlled by other fields
    # such as `sampling_percent`, `row_filter`, and column filters.
    # This mode allows for full scans or custom sampling.
    STANDARD = 1

    # Specifies lightweight profiling mode. This mode is optimized for
    # low-latency, low-fidelity profiling.
    #
    # When this mode is selected, the following fields must not be set:
    # `sampling_percent`, `row_filter`, `include_fields`, and `exclude_fields`.
    LIGHTWEIGHT = 2
  end
end

#exclude_fields ⇒ ::Google::Cloud::Dataplex::V1::DataProfileSpec::SelectedFields

Returns Optional. The fields to exclude from data profile.

If specified, the fields will be excluded from data profile, regardless of include_fields value.

Returns:



62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
# File 'proto_docs/google/cloud/dataplex/v1/data_profile.rb', line 62

class DataProfileSpec
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The configuration of post scan actions of DataProfileScan job.
  # @!attribute [rw] bigquery_export
  #   @return [::Google::Cloud::Dataplex::V1::DataProfileSpec::PostScanActions::BigQueryExport]
  #     Optional. If set, results will be exported to the provided BigQuery
  #     table.
  class PostScanActions
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The configuration of BigQuery export post scan action.
    # @!attribute [rw] results_table
    #   @return [::String]
    #     Optional. The BigQuery table to export DataProfileScan results to.
    #     Format:
    #     //bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
    class BigQueryExport
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # The specification for fields to include or exclude in data profile scan.
  # @!attribute [rw] field_names
  #   @return [::Array<::String>]
  #     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'.
  class SelectedFields
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Defines the execution mode for the profile scan.
  module Mode
    # Default value. This value is unused.
    MODE_UNSPECIFIED = 0

    # Performs standard profiling. The behavior is controlled by other fields
    # such as `sampling_percent`, `row_filter`, and column filters.
    # This mode allows for full scans or custom sampling.
    STANDARD = 1

    # Specifies lightweight profiling mode. This mode is optimized for
    # low-latency, low-fidelity profiling.
    #
    # When this mode is selected, the following fields must not be set:
    # `sampling_percent`, `row_filter`, `include_fields`, and `exclude_fields`.
    LIGHTWEIGHT = 2
  end
end

#include_fields ⇒ ::Google::Cloud::Dataplex::V1::DataProfileSpec::SelectedFields

Returns 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.

Returns:



62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
# File 'proto_docs/google/cloud/dataplex/v1/data_profile.rb', line 62

class DataProfileSpec
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The configuration of post scan actions of DataProfileScan job.
  # @!attribute [rw] bigquery_export
  #   @return [::Google::Cloud::Dataplex::V1::DataProfileSpec::PostScanActions::BigQueryExport]
  #     Optional. If set, results will be exported to the provided BigQuery
  #     table.
  class PostScanActions
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The configuration of BigQuery export post scan action.
    # @!attribute [rw] results_table
    #   @return [::String]
    #     Optional. The BigQuery table to export DataProfileScan results to.
    #     Format:
    #     //bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
    class BigQueryExport
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # The specification for fields to include or exclude in data profile scan.
  # @!attribute [rw] field_names
  #   @return [::Array<::String>]
  #     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'.
  class SelectedFields
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Defines the execution mode for the profile scan.
  module Mode
    # Default value. This value is unused.
    MODE_UNSPECIFIED = 0

    # Performs standard profiling. The behavior is controlled by other fields
    # such as `sampling_percent`, `row_filter`, and column filters.
    # This mode allows for full scans or custom sampling.
    STANDARD = 1

    # Specifies lightweight profiling mode. This mode is optimized for
    # low-latency, low-fidelity profiling.
    #
    # When this mode is selected, the following fields must not be set:
    # `sampling_percent`, `row_filter`, `include_fields`, and `exclude_fields`.
    LIGHTWEIGHT = 2
  end
end

#mode ⇒ ::Google::Cloud::Dataplex::V1::DataProfileSpec::Mode

Returns Optional. The execution mode for the profile scan.

Returns:



62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
# File 'proto_docs/google/cloud/dataplex/v1/data_profile.rb', line 62

class DataProfileSpec
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The configuration of post scan actions of DataProfileScan job.
  # @!attribute [rw] bigquery_export
  #   @return [::Google::Cloud::Dataplex::V1::DataProfileSpec::PostScanActions::BigQueryExport]
  #     Optional. If set, results will be exported to the provided BigQuery
  #     table.
  class PostScanActions
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The configuration of BigQuery export post scan action.
    # @!attribute [rw] results_table
    #   @return [::String]
    #     Optional. The BigQuery table to export DataProfileScan results to.
    #     Format:
    #     //bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
    class BigQueryExport
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # The specification for fields to include or exclude in data profile scan.
  # @!attribute [rw] field_names
  #   @return [::Array<::String>]
  #     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'.
  class SelectedFields
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Defines the execution mode for the profile scan.
  module Mode
    # Default value. This value is unused.
    MODE_UNSPECIFIED = 0

    # Performs standard profiling. The behavior is controlled by other fields
    # such as `sampling_percent`, `row_filter`, and column filters.
    # This mode allows for full scans or custom sampling.
    STANDARD = 1

    # Specifies lightweight profiling mode. This mode is optimized for
    # low-latency, low-fidelity profiling.
    #
    # When this mode is selected, the following fields must not be set:
    # `sampling_percent`, `row_filter`, `include_fields`, and `exclude_fields`.
    LIGHTWEIGHT = 2
  end
end

#post_scan_actions ⇒ ::Google::Cloud::Dataplex::V1::DataProfileSpec::PostScanActions

Returns Optional. Actions to take upon job completion..

Returns:



62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
# File 'proto_docs/google/cloud/dataplex/v1/data_profile.rb', line 62

class DataProfileSpec
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The configuration of post scan actions of DataProfileScan job.
  # @!attribute [rw] bigquery_export
  #   @return [::Google::Cloud::Dataplex::V1::DataProfileSpec::PostScanActions::BigQueryExport]
  #     Optional. If set, results will be exported to the provided BigQuery
  #     table.
  class PostScanActions
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The configuration of BigQuery export post scan action.
    # @!attribute [rw] results_table
    #   @return [::String]
    #     Optional. The BigQuery table to export DataProfileScan results to.
    #     Format:
    #     //bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
    class BigQueryExport
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # The specification for fields to include or exclude in data profile scan.
  # @!attribute [rw] field_names
  #   @return [::Array<::String>]
  #     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'.
  class SelectedFields
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Defines the execution mode for the profile scan.
  module Mode
    # Default value. This value is unused.
    MODE_UNSPECIFIED = 0

    # Performs standard profiling. The behavior is controlled by other fields
    # such as `sampling_percent`, `row_filter`, and column filters.
    # This mode allows for full scans or custom sampling.
    STANDARD = 1

    # Specifies lightweight profiling mode. This mode is optimized for
    # low-latency, low-fidelity profiling.
    #
    # When this mode is selected, the following fields must not be set:
    # `sampling_percent`, `row_filter`, `include_fields`, and `exclude_fields`.
    LIGHTWEIGHT = 2
  end
end

#row_filter ⇒ ::String

Returns 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.

Returns:

  • (::String) —

    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



62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
# File 'proto_docs/google/cloud/dataplex/v1/data_profile.rb', line 62

class DataProfileSpec
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The configuration of post scan actions of DataProfileScan job.
  # @!attribute [rw] bigquery_export
  #   @return [::Google::Cloud::Dataplex::V1::DataProfileSpec::PostScanActions::BigQueryExport]
  #     Optional. If set, results will be exported to the provided BigQuery
  #     table.
  class PostScanActions
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The configuration of BigQuery export post scan action.
    # @!attribute [rw] results_table
    #   @return [::String]
    #     Optional. The BigQuery table to export DataProfileScan results to.
    #     Format:
    #     //bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
    class BigQueryExport
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # The specification for fields to include or exclude in data profile scan.
  # @!attribute [rw] field_names
  #   @return [::Array<::String>]
  #     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'.
  class SelectedFields
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Defines the execution mode for the profile scan.
  module Mode
    # Default value. This value is unused.
    MODE_UNSPECIFIED = 0

    # Performs standard profiling. The behavior is controlled by other fields
    # such as `sampling_percent`, `row_filter`, and column filters.
    # This mode allows for full scans or custom sampling.
    STANDARD = 1

    # Specifies lightweight profiling mode. This mode is optimized for
    # low-latency, low-fidelity profiling.
    #
    # When this mode is selected, the following fields must not be set:
    # `sampling_percent`, `row_filter`, `include_fields`, and `exclude_fields`.
    LIGHTWEIGHT = 2
  end
end

#sampling_percent ⇒ ::Float

Returns 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.

Returns:

  • (::Float) —

    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.


62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
# File 'proto_docs/google/cloud/dataplex/v1/data_profile.rb', line 62

class DataProfileSpec
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The configuration of post scan actions of DataProfileScan job.
  # @!attribute [rw] bigquery_export
  #   @return [::Google::Cloud::Dataplex::V1::DataProfileSpec::PostScanActions::BigQueryExport]
  #     Optional. If set, results will be exported to the provided BigQuery
  #     table.
  class PostScanActions
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The configuration of BigQuery export post scan action.
    # @!attribute [rw] results_table
    #   @return [::String]
    #     Optional. The BigQuery table to export DataProfileScan results to.
    #     Format:
    #     //bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET_ID/tables/TABLE_ID
    class BigQueryExport
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end

  # The specification for fields to include or exclude in data profile scan.
  # @!attribute [rw] field_names
  #   @return [::Array<::String>]
  #     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'.
  class SelectedFields
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Defines the execution mode for the profile scan.
  module Mode
    # Default value. This value is unused.
    MODE_UNSPECIFIED = 0

    # Performs standard profiling. The behavior is controlled by other fields
    # such as `sampling_percent`, `row_filter`, and column filters.
    # This mode allows for full scans or custom sampling.
    STANDARD = 1

    # Specifies lightweight profiling mode. This mode is optimized for
    # low-latency, low-fidelity profiling.
    #
    # When this mode is selected, the following fields must not be set:
    # `sampling_percent`, `row_filter`, `include_fields`, and `exclude_fields`.
    LIGHTWEIGHT = 2
  end
end