google-cloud-bigquery 1.27.0 → 1.32.0

data/lib/google/cloud/bigquery/extract_job.rb

@@ -246,6 +246,7 @@ module Google
           ##
           # @private Create an Updater object.
           def initialize gapi
+            super()
             @gapi = gapi
           end
 
@@ -263,9 +264,10 @@ module Google
             extract_config = Google::Apis::BigqueryV2::JobConfigurationExtract.new(
               destination_uris: Array(storage_urls)
             )
-            if source.is_a? Google::Apis::BigqueryV2::TableReference
+            case source
+            when Google::Apis::BigqueryV2::TableReference
               extract_config.source_table = source
-            elsif source.is_a? Google::Apis::BigqueryV2::ModelReference
+            when Google::Apis::BigqueryV2::ModelReference
               extract_config.source_model = source
             end
             job = Google::Apis::BigqueryV2::Job.new(

data/lib/google/cloud/bigquery/job.rb

@@ -507,7 +507,8 @@ module Google
         # @attr_reader [Fixnum] slot_ms The slot-milliseconds the job spent in the given reservation.
         #
         class ReservationUsage
-          attr_reader :name, :slot_ms
+          attr_reader :name
+          attr_reader :slot_ms
 
           ##
           # @private Creates a new ReservationUsage instance.
@@ -571,7 +572,8 @@ module Google
         #   end
         #
         class ScriptStatistics
-          attr_reader :evaluation_kind, :stack_frames
+          attr_reader :evaluation_kind
+          attr_reader :stack_frames
 
           ##
           # @private Creates a new ScriptStatistics instance.
@@ -636,7 +638,11 @@ module Google
         #   end
         #
         class ScriptStackFrame
-          attr_reader :start_line, :start_column, :end_line, :end_column, :text
+          attr_reader :start_line
+          attr_reader :start_column
+          attr_reader :end_line
+          attr_reader :end_column
+          attr_reader :text
 
           ##
           # @private Creates a new ScriptStackFrame instance.

data/lib/google/cloud/bigquery/job/list.rb

@@ -72,8 +72,8 @@ module Google
             return nil unless next?
             ensure_service!
             next_kwargs = @kwargs.merge token: token
-            next_gapi = @service.list_jobs next_kwargs
-            self.class.from_gapi next_gapi, @service, next_kwargs
+            next_gapi = @service.list_jobs(**next_kwargs)
+            self.class.from_gapi next_gapi, @service, **next_kwargs
           end
 
           ##
@@ -121,12 +121,12 @@ module Google
           #     puts job.state
           #   end
           #
-          def all request_limit: nil
+          def all request_limit: nil, &block
             request_limit = request_limit.to_i if request_limit
             return enum_for :all, request_limit: request_limit unless block_given?
             results = self
             loop do
-              results.each { |r| yield r }
+              results.each(&block)
               if request_limit
                 request_limit -= 1
                 break if request_limit.negative?

data/lib/google/cloud/bigquery/load_job.rb

@@ -416,6 +416,49 @@ module Google
           @gapi.configuration.load.hive_partitioning_options.source_uri_prefix if hive_partitioning?
         end
 
+        ###
+        # Checks if Parquet options are set.
+        #
+        # @see https://cloud.google.com/bigquery/docs/loading-data-cloud-storage-parquet Loading Parquet data from Cloud
+        #   Storage
+        #
+        # @return [Boolean] `true` when Parquet options are set, or `false` otherwise.
+        #
+        # @!group Attributes
+        #
+        def parquet_options?
+          !@gapi.configuration.load.parquet_options.nil?
+        end
+
+        ###
+        # Indicates whether to use schema inference specifically for Parquet `LIST` logical type.
+        #
+        # @see https://cloud.google.com/bigquery/docs/loading-data-cloud-storage-parquet Loading Parquet data from Cloud
+        #   Storage
+        #
+        # @return [Boolean, nil] The `enable_list_inference` value in Parquet options, or `nil` if Parquet options are
+        #   not set.
+        #
+        # @!group Attributes
+        #
+        def parquet_enable_list_inference?
+          @gapi.configuration.load.parquet_options.enable_list_inference if parquet_options?
+        end
+
+        ###
+        # Indicates whether to infer Parquet `ENUM` logical type as `STRING` instead of `BYTES` by default.
+        #
+        # @see https://cloud.google.com/bigquery/docs/loading-data-cloud-storage-parquet Loading Parquet data from Cloud
+        #   Storage
+        #
+        # @return [Boolean, nil] The `enum_as_string` value in Parquet options, or `nil` if Parquet options are not set.
+        #
+        # @!group Attributes
+        #
+        def parquet_enum_as_string?
+          @gapi.configuration.load.parquet_options.enum_as_string if parquet_options?
+        end
+
         ###
         # Checks if the destination table will be range partitioned. See [Creating and using integer range partitioned
         # tables](https://cloud.google.com/bigquery/docs/creating-integer-range-partitions).
@@ -484,7 +527,7 @@ module Google
         # Checks if the destination table will be time partitioned. See
         # [Partitioned Tables](https://cloud.google.com/bigquery/docs/partitioned-tables).
         #
-        # @return [Boolean, nil] `true` when the table will be time-partitioned,
+        # @return [Boolean] `true` when the table will be time-partitioned,
         #   or `false` otherwise.
         #
         # @!group Attributes
@@ -560,10 +603,15 @@ module Google
         ###
         # Checks if the destination table will be clustered.
         #
+        # See {LoadJob::Updater#clustering_fields=}, {Table#clustering_fields} and
+        # {Table#clustering_fields=}.
+        #
         # @see https://cloud.google.com/bigquery/docs/clustered-tables
-        #   Introduction to Clustered Tables
+        #   Introduction to clustered tables
+        # @see https://cloud.google.com/bigquery/docs/creating-clustered-tables
+        #   Creating and using clustered tables
         #
-        # @return [Boolean, nil] `true` when the table will be clustered,
+        # @return [Boolean] `true` when the table will be clustered,
         #   or `false` otherwise.
         #
         # @!group Attributes
@@ -578,14 +626,16 @@ module Google
         # be first partitioned and subsequently clustered. The order of the
         # returned fields determines the sort order of the data.
         #
-        # See {LoadJob::Updater#clustering_fields=}.
+        # BigQuery supports clustering for both partitioned and non-partitioned
+        # tables.
+        #
+        # See {LoadJob::Updater#clustering_fields=}, {Table#clustering_fields} and
+        # {Table#clustering_fields=}.
         #
-        # @see https://cloud.google.com/bigquery/docs/partitioned-tables
-        #   Partitioned Tables
         # @see https://cloud.google.com/bigquery/docs/clustered-tables
-        #   Introduction to Clustered Tables
+        #   Introduction to clustered tables
         # @see https://cloud.google.com/bigquery/docs/creating-clustered-tables
-        #   Creating and Using Clustered Tables
+        #   Creating and using clustered tables
         #
         # @return [Array<String>, nil] The clustering fields, or `nil` if the
         #   destination table will not be clustered.
@@ -606,6 +656,7 @@ module Google
           ##
           # @private Create an Updater object.
           def initialize gapi
+            super()
             @updates = []
             @gapi = gapi
             @schema = nil
@@ -772,9 +823,18 @@ module Google
           end
 
           ##
-          # Adds a numeric number field to the schema. Numeric is a
-          # fixed-precision numeric type with 38 decimal digits, 9 that follow
-          # the decimal point.
+          # Adds a numeric number field to the schema. `NUMERIC` is a decimal
+          # type with fixed precision and scale. Precision is the number of
+          # digits that the number contains. Scale is how many of these
+          # digits appear after the decimal point. It supports:
+          #
+          # Precision: 38
+          # Scale: 9
+          # Min: -9.9999999999999999999999999999999999999E+28
+          # Max: 9.9999999999999999999999999999999999999E+28
+          #
+          # This type can represent decimal fractions exactly, and is suitable
+          # for financial calculations.
           #
           # See {Schema#numeric}
           #
@@ -801,6 +861,45 @@ module Google
             schema.numeric name, description: description, mode: mode
           end
 
+          ##
+          # Adds a bignumeric number field to the schema. `BIGNUMERIC` is a
+          # decimal type with fixed precision and scale. Precision is the
+          # number of digits that the number contains. Scale is how many of
+          # these digits appear after the decimal point. It supports:
+          #
+          # Precision: 76.76 (the 77th digit is partial)
+          # Scale: 38
+          # Min: -5.7896044618658097711785492504343953926634992332820282019728792003956564819968E+38
+          # Max: 5.7896044618658097711785492504343953926634992332820282019728792003956564819967E+38
+          #
+          # This type can represent decimal fractions exactly, and is suitable
+          # for financial calculations.
+          #
+          # See {Schema#bignumeric}
+          #
+          # @param [String] name The field name. The name must contain only
+          #   letters (a-z, A-Z), numbers (0-9), or underscores (_), and must
+          #   start with a letter or underscore. The maximum length is 128
+          #   characters.
+          # @param [String] description A description of the field.
+          # @param [Symbol] mode The field's mode. The possible values are
+          #   `:nullable`, `:required`, and `:repeated`. The default value is
+          #   `:nullable`.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #   dataset = bigquery.dataset "my_dataset"
+          #   job = dataset.load_job "my_table", "gs://abc/file" do |schema|
+          #     schema.bignumeric "total_cost", mode: :required
+          #   end
+          #
+          # @!group Schema
+          def bignumeric name, description: nil, mode: :nullable
+            schema.bignumeric name, description: description, mode: mode
+          end
+
           ##
           # Adds a boolean field to the schema.
           #
@@ -1478,6 +1577,66 @@ module Google
             @gapi.configuration.load.hive_partitioning_options.source_uri_prefix = source_uri_prefix
           end
 
+          ##
+          # Sets whether to use schema inference specifically for Parquet `LIST` logical type.
+          #
+          # @see https://cloud.google.com/bigquery/docs/loading-data-cloud-storage-parquet Loading Parquet data from
+          #   Cloud Storage
+          #
+          # @param [Boolean] enable_list_inference The `enable_list_inference` value to use in Parquet options.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #   dataset = bigquery.dataset "my_dataset"
+          #
+          #   gcs_uris = ["gs://mybucket/00/*.parquet", "gs://mybucket/01/*.parquet"]
+          #   load_job = dataset.load_job "my_new_table", gcs_uris do |job|
+          #     job.format = :parquet
+          #     job.parquet_enable_list_inference = true
+          #   end
+          #
+          #   load_job.wait_until_done!
+          #   load_job.done? #=> true
+          #
+          # @!group Attributes
+          #
+          def parquet_enable_list_inference= enable_list_inference
+            @gapi.configuration.load.parquet_options ||= Google::Apis::BigqueryV2::ParquetOptions.new
+            @gapi.configuration.load.parquet_options.enable_list_inference = enable_list_inference
+          end
+
+          ##
+          # Sets whether to infer Parquet `ENUM` logical type as `STRING` instead of `BYTES` by default.
+          #
+          # @see https://cloud.google.com/bigquery/docs/loading-data-cloud-storage-parquet Loading Parquet data from
+          #   Cloud Storage
+          #
+          # @param [Boolean] enum_as_string The `enum_as_string` value to use in Parquet options.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #   dataset = bigquery.dataset "my_dataset"
+          #
+          #   gcs_uris = ["gs://mybucket/00/*.parquet", "gs://mybucket/01/*.parquet"]
+          #   load_job = dataset.load_job "my_new_table", gcs_uris do |job|
+          #     job.format = :parquet
+          #     job.parquet_enum_as_string = true
+          #   end
+          #
+          #   load_job.wait_until_done!
+          #   load_job.done? #=> true
+          #
+          # @!group Attributes
+          #
+          def parquet_enum_as_string= enum_as_string
+            @gapi.configuration.load.parquet_options ||= Google::Apis::BigqueryV2::ParquetOptions.new
+            @gapi.configuration.load.parquet_options.enum_as_string = enum_as_string
+          end
+
           ##
           # Sets the field on which to range partition the table. See [Creating and using integer range partitioned
           # tables](https://cloud.google.com/bigquery/docs/creating-integer-range-partitions).
@@ -1770,23 +1929,23 @@ module Google
           end
 
           ##
-          # Sets one or more fields on which the destination table should be
-          # clustered. Must be specified with time-based partitioning, data in
-          # the table will be first partitioned and subsequently clustered.
+          # Sets the list of fields on which data should be clustered.
           #
           # Only top-level, non-repeated, simple-type fields are supported. When
           # you cluster a table using multiple columns, the order of columns you
           # specify is important. The order of the specified columns determines
           # the sort order of the data.
           #
-          # See {LoadJob#clustering_fields}.
+          # BigQuery supports clustering for both partitioned and non-partitioned
+          # tables.
+          #
+          # See {LoadJob#clustering_fields}, {Table#clustering_fields} and
+          # {Table#clustering_fields=}.
           #
-          # @see https://cloud.google.com/bigquery/docs/partitioned-tables
-          #   Partitioned Tables
           # @see https://cloud.google.com/bigquery/docs/clustered-tables
-          #   Introduction to Clustered Tables
+          #   Introduction to clustered tables
           # @see https://cloud.google.com/bigquery/docs/creating-clustered-tables
-          #   Creating and Using Clustered Tables
+          #   Creating and using clustered tables
           #
           # @param [Array<String>] fields The clustering fields. Only top-level,
           #   non-repeated, simple-type fields are supported.

data/lib/google/cloud/bigquery/model/list.rb

@@ -124,12 +124,12 @@ module Google
           #     puts model.model_id
           #   end
           #
-          def all request_limit: nil
+          def all request_limit: nil, &block
             request_limit = request_limit.to_i if request_limit
             return enum_for :all, request_limit: request_limit unless block_given?
             results = self
             loop do
-              results.each { |r| yield r }
+              results.each(&block)
               if request_limit
                 request_limit -= 1
                 break if request_limit.negative?

data/lib/google/cloud/bigquery/policy.rb

@@ -96,7 +96,8 @@ module Google
       #   end
       #
       class Policy
-        attr_reader :etag, :bindings
+        attr_reader :etag
+        attr_reader :bindings
 
         # @private
         def initialize etag, bindings

data/lib/google/cloud/bigquery/project.rb

@@ -56,7 +56,8 @@ module Google
         # @private The Service object.
         attr_accessor :service
 
-        attr_reader :name, :numeric_id
+        attr_reader :name
+        attr_reader :numeric_id
 
         ##
         # Creates a new Service instance.
@@ -292,35 +293,37 @@ module Google
         #
         #   Ruby types are mapped to BigQuery types as follows:
         #
-        #   | BigQuery    | Ruby                                 | Notes                                          |
-        #   |-------------|--------------------------------------|------------------------------------------------|
-        #   | `BOOL`      | `true`/`false`                       |                                                |
-        #   | `INT64`     | `Integer`                            |                                                |
-        #   | `FLOAT64`   | `Float`                              |                                                |
-        #   | `NUMERIC`   | `BigDecimal`                         | Will be rounded to 9 decimal places            |
-        #   | `STRING`    | `String`                             |                                                |
-        #   | `DATETIME`  | `DateTime`                           | `DATETIME` does not support time zone.         |
-        #   | `DATE`      | `Date`                               |                                                |
-        #   | `TIMESTAMP` | `Time`                               |                                                |
-        #   | `TIME`      | `Google::Cloud::BigQuery::Time`      |                                                |
-        #   | `BYTES`     | `File`, `IO`, `StringIO`, or similar |                                                |
-        #   | `ARRAY`     | `Array`                              | Nested arrays, `nil` values are not supported. |
-        #   | `STRUCT`    | `Hash`                               | Hash keys may be strings or symbols.           |
+        #   | BigQuery     | Ruby                                 | Notes                                              |
+        #   |--------------|--------------------------------------|----------------------------------------------------|
+        #   | `BOOL`       | `true`/`false`                       |                                                    |
+        #   | `INT64`      | `Integer`                            |                                                    |
+        #   | `FLOAT64`    | `Float`                              |                                                    |
+        #   | `NUMERIC`    | `BigDecimal`                         | `BigDecimal` values will be rounded to scale 9.    |
+        #   | `BIGNUMERIC` |                                      | Query param values must be mapped in `types`.      |
+        #   | `STRING`     | `String`                             |                                                    |
+        #   | `DATETIME`   | `DateTime`                           | `DATETIME` does not support time zone.             |
+        #   | `DATE`       | `Date`                               |                                                    |
+        #   | `TIMESTAMP`  | `Time`                               |                                                    |
+        #   | `TIME`       | `Google::Cloud::BigQuery::Time`      |                                                    |
+        #   | `BYTES`      | `File`, `IO`, `StringIO`, or similar |                                                    |
+        #   | `ARRAY`      | `Array`                              | Nested arrays, `nil` values are not supported.     |
+        #   | `STRUCT`     | `Hash`                               | Hash keys may be strings or symbols.               |
         #
         #   See [Data Types](https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types) for an overview
         #   of each BigQuery data type, including allowed values.
-        # @param [Array, Hash] types Standard SQL only. Types of the SQL parameters in `params`. It is not always to
-        #   infer the right SQL type from a value in `params`. In these cases, `types` must be used to specify the SQL
-        #   type for these values.
+        # @param [Array, Hash] types Standard SQL only. Types of the SQL parameters in `params`. It is not always
+        #   possible to infer the right SQL type from a value in `params`. In these cases, `types` must be used to
+        #   specify the SQL type for these values.
         #
-        #   Must match the value type passed to `params`. This must be an `Array` when the query uses positional query
-        #   parameters. This must be an `Hash` when the query uses named query parameters. The values should be BigQuery
-        #   type codes from the following list:
+        #   Arguments must match the value type passed to `params`. This must be an `Array` when the query uses
+        #   positional query parameters. This must be an `Hash` when the query uses named query parameters. The values
+        #   should be BigQuery type codes from the following list:
         #
         #   * `:BOOL`
         #   * `:INT64`
         #   * `:FLOAT64`
         #   * `:NUMERIC`
+        #   * `:BIGNUMERIC`
         #   * `:STRING`
         #   * `:DATETIME`
         #   * `:DATE`
@@ -637,35 +640,37 @@ module Google
         #
         #   Ruby types are mapped to BigQuery types as follows:
         #
-        #   | BigQuery    | Ruby                                 | Notes                                          |
-        #   |-------------|--------------------------------------|------------------------------------------------|
-        #   | `BOOL`      | `true`/`false`                       |                                                |
-        #   | `INT64`     | `Integer`                            |                                                |
-        #   | `FLOAT64`   | `Float`                              |                                                |
-        #   | `NUMERIC`   | `BigDecimal`                         | Will be rounded to 9 decimal places            |
-        #   | `STRING`    | `String`                             |                                                |
-        #   | `DATETIME`  | `DateTime`                           | `DATETIME` does not support time zone.         |
-        #   | `DATE`      | `Date`                               |                                                |
-        #   | `TIMESTAMP` | `Time`                               |                                                |
-        #   | `TIME`      | `Google::Cloud::BigQuery::Time`      |                                                |
-        #   | `BYTES`     | `File`, `IO`, `StringIO`, or similar |                                                |
-        #   | `ARRAY`     | `Array`                              | Nested arrays, `nil` values are not supported. |
-        #   | `STRUCT`    | `Hash`                               | Hash keys may be strings or symbols.           |
+        #   | BigQuery     | Ruby                                 | Notes                                              |
+        #   |--------------|--------------------------------------|----------------------------------------------------|
+        #   | `BOOL`       | `true`/`false`                       |                                                    |
+        #   | `INT64`      | `Integer`                            |                                                    |
+        #   | `FLOAT64`    | `Float`                              |                                                    |
+        #   | `NUMERIC`    | `BigDecimal`                         | `BigDecimal` values will be rounded to scale 9.    |
+        #   | `BIGNUMERIC` |                                      | Query param values must be mapped in `types`.      |
+        #   | `STRING`     | `String`                             |                                                    |
+        #   | `DATETIME`   | `DateTime`                           | `DATETIME` does not support time zone.             |
+        #   | `DATE`       | `Date`                               |                                                    |
+        #   | `TIMESTAMP`  | `Time`                               |                                                    |
+        #   | `TIME`       | `Google::Cloud::BigQuery::Time`      |                                                    |
+        #   | `BYTES`      | `File`, `IO`, `StringIO`, or similar |                                                    |
+        #   | `ARRAY`      | `Array`                              | Nested arrays, `nil` values are not supported.     |
+        #   | `STRUCT`     | `Hash`                               | Hash keys may be strings or symbols.               |
         #
         #   See [Data Types](https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types) for an overview
         #   of each BigQuery data type, including allowed values.
-        # @param [Array, Hash] types Standard SQL only. Types of the SQL parameters in `params`. It is not always to
-        #   infer the right SQL type from a value in `params`. In these cases, `types` must be used to specify the SQL
-        #   type for these values.
+        # @param [Array, Hash] types Standard SQL only. Types of the SQL parameters in `params`. It is not always
+        #   possible to infer the right SQL type from a value in `params`. In these cases, `types` must be used to
+        #   specify the SQL type for these values.
         #
-        #   Must match the value type passed to `params`. This must be an `Array` when the query uses positional query
-        #   parameters. This must be an `Hash` when the query uses named query parameters. The values should be BigQuery
-        #   type codes from the following list:
+        #   Arguments must match the value type passed to `params`. This must be an `Array` when the query uses
+        #   positional query parameters. This must be an `Hash` when the query uses named query parameters. The values
+        #   should be BigQuery type codes from the following list:
         #
         #   * `:BOOL`
         #   * `:INT64`
         #   * `:FLOAT64`
         #   * `:NUMERIC`
+        #   * `:BIGNUMERIC`
         #   * `:STRING`
         #   * `:DATETIME`
         #   * `:DATE`
@@ -981,8 +986,7 @@ module Google
         # @param [String] description A user-friendly description of the
         #   dataset.
         # @param [Integer] expiration The default lifetime of all tables in the
-        #   dataset, in milliseconds. The minimum value is 3600000 milliseconds
-        #   (one hour).
+        #   dataset, in milliseconds. The minimum value is `3_600_000` (one hour).
         # @param [String] location The geographic location where the dataset
         #   should reside. Possible values include `EU` and `US`. The default
         #   value is `US`.