google-cloud-bigquery 1.25.0 → 1.30.0

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

@@ -482,14 +482,14 @@ module Google
         #     puts row[:word]
         #   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/dataset.rb

@@ -618,15 +618,17 @@ module Google
         end
 
         ##
-        # Creates a new [view](https://cloud.google.com/bigquery/docs/views)
-        # table, which is a virtual table defined by the given SQL query.
+        # Creates a new view, which is a virtual table defined by the given SQL query.
         #
-        # BigQuery's views are logical views, not materialized views, which
-        # means that the query that defines the view is re-executed every time
-        # the view is queried. Queries are billed according to the total amount
+        # With BigQuery's logical views, the query that defines the view is re-executed
+        # every time the view is queried. Queries are billed according to the total amount
         # of data in all table fields referenced directly or indirectly by the
         # top-level query. (See {Table#view?} and {Table#query}.)
         #
+        # For materialized views, see {#create_materialized_view}.
+        #
+        # @see https://cloud.google.com/bigquery/docs/views Creating views
+        #
         # @param [String] table_id The ID of the view table. The ID must contain
         #   only letters (a-z, A-Z), numbers (0-9), or underscores (_). The
         #   maximum length is 1,024 characters.
@@ -667,7 +669,7 @@ module Google
         #   dataset = bigquery.dataset "my_dataset"
         #
         #   view = dataset.create_view "my_view",
-        #             "SELECT name, age FROM proj.dataset.users"
+        #                              "SELECT name, age FROM proj.dataset.users"
         #
         # @example A name and description can be provided:
         #   require "google/cloud/bigquery"
@@ -676,13 +678,18 @@ module Google
         #   dataset = bigquery.dataset "my_dataset"
         #
         #   view = dataset.create_view "my_view",
-        #             "SELECT name, age FROM proj.dataset.users",
-        #             name: "My View", description: "This is my view"
+        #                              "SELECT name, age FROM proj.dataset.users",
+        #                              name: "My View", description: "This is my view"
         #
         # @!group Table
         #
-        def create_view table_id, query, name: nil, description: nil,
-                        standard_sql: nil, legacy_sql: nil, udfs: nil
+        def create_view table_id,
+                        query,
+                        name: nil,
+                        description: nil,
+                        standard_sql: nil,
+                        legacy_sql: nil,
+                        udfs: nil
           use_legacy_sql = Convert.resolve_legacy_sql standard_sql, legacy_sql
           new_view_opts = {
             table_reference: Google::Apis::BigqueryV2::TableReference.new(
@@ -698,7 +705,81 @@ module Google
               user_defined_function_resources: udfs_gapi(udfs)
             )
           }.delete_if { |_, v| v.nil? }
-          new_view = Google::Apis::BigqueryV2::Table.new new_view_opts
+          new_view = Google::Apis::BigqueryV2::Table.new(**new_view_opts)
+
+          gapi = service.insert_table dataset_id, new_view
+          Table.from_gapi gapi, service
+        end
+
+        ##
+        # Creates a new materialized view.
+        #
+        # Materialized views are precomputed views that periodically cache results of a query for increased performance
+        # and efficiency. BigQuery leverages precomputed results from materialized views and whenever possible reads
+        # only delta changes from the base table to compute up-to-date results.
+        #
+        # Queries that use materialized views are generally faster and consume less resources than queries that retrieve
+        # the same data only from the base table. Materialized views are helpful to significantly boost performance of
+        # workloads that have the characteristic of common and repeated queries.
+        #
+        # For logical views, see {#create_view}.
+        #
+        # @see https://cloud.google.com/bigquery/docs/materialized-views-intro Introduction to materialized views
+        #
+        # @param [String] table_id The ID of the materialized view table. The ID must contain only letters (a-z, A-Z),
+        #   numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+        # @param [String] query The query that BigQuery executes when the materialized view is referenced.
+        # @param [String] name A descriptive name for the table.
+        # @param [String] description A user-friendly description of the table.
+        # @param [Boolean] enable_refresh Enable automatic refresh of the materialized view when the base table is
+        #   updated. Optional. The default value is true.
+        # @param [Integer] refresh_interval_ms The maximum frequency in milliseconds at which this materialized view
+        #   will be refreshed. Optional. The default value is `1_800_000` (30 minutes).
+        #
+        # @return [Google::Cloud::Bigquery::Table] A new table object.
+        #
+        # @example
+        #   require "google/cloud/bigquery"
+        #
+        #   bigquery = Google::Cloud::Bigquery.new
+        #   dataset = bigquery.dataset "my_dataset"
+        #
+        #   materialized_view = dataset.create_materialized_view "my_materialized_view",
+        #                                                        "SELECT name, age FROM proj.dataset.users"
+        #
+        # @example Automatic refresh can be disabled:
+        #   require "google/cloud/bigquery"
+        #
+        #   bigquery = Google::Cloud::Bigquery.new
+        #   dataset = bigquery.dataset "my_dataset"
+        #
+        #   materialized_view = dataset.create_materialized_view "my_materialized_view",
+        #                                                        "SELECT name, age FROM proj.dataset.users",
+        #                                                        enable_refresh: false
+        #
+        # @!group Table
+        #
+        def create_materialized_view table_id,
+                                     query,
+                                     name: nil,
+                                     description: nil,
+                                     enable_refresh: nil,
+                                     refresh_interval_ms: nil
+          new_view_opts = {
+            table_reference:   Google::Apis::BigqueryV2::TableReference.new(
+              project_id: project_id,
+              dataset_id: dataset_id,
+              table_id:   table_id
+            ),
+            friendly_name:     name,
+            description:       description,
+            materialized_view: Google::Apis::BigqueryV2::MaterializedViewDefinition.new(
+              enable_refresh:      enable_refresh,
+              query:               query,
+              refresh_interval_ms: refresh_interval_ms
+            )
+          }.delete_if { |_, v| v.nil? }
+          new_view = Google::Apis::BigqueryV2::Table.new(**new_view_opts)
 
           gapi = service.insert_table dataset_id, new_view
           Table.from_gapi gapi, service
@@ -1059,35 +1140,37 @@ 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`
@@ -1400,35 +1483,37 @@ 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`
@@ -2327,6 +2412,21 @@ module Google
         # the need to complete a load operation before the data can appear in
         # query results.
         #
+        # Simple Ruby types are generally accepted per JSON rules, along with the following support for BigQuery's more
+        # complex types:
+        #
+        # | BigQuery     | Ruby                                 | Notes                                              |
+        # |--------------|--------------------------------------|----------------------------------------------------|
+        # | `NUMERIC`    | `BigDecimal`                         | `BigDecimal` values will be rounded to scale 9.    |
+        # | `BIGNUMERIC` | `String`                             | Pass as `String` to avoid rounding to scale 9.     |
+        # | `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.               |
+        #
         # Because BigQuery's streaming API is designed for high insertion rates,
         # modifications to the underlying table metadata are eventually
         # consistent when interacting with the streaming system. In most cases
@@ -2341,7 +2441,10 @@ module Google
         #
         # @param [String] table_id The ID of the destination table.
         # @param [Hash, Array<Hash>] rows A hash object or array of hash objects
-        #   containing the data. Required.
+        #   containing the data. Required. `BigDecimal` values will be rounded to
+        #   scale 9 to conform with the BigQuery `NUMERIC` data type. To avoid
+        #   rounding `BIGNUMERIC` type values with scale greater than 9, use `String`
+        #   instead of `BigDecimal`.
         # @param [Array<String|Symbol>, Symbol] insert_ids A unique ID for each row. BigQuery uses this property to
         #   detect duplicate insertion requests on a best-effort basis. For more information, see [data
         #   consistency](https://cloud.google.com/bigquery/streaming-data-into-bigquery#dataconsistency). Optional. If
@@ -2408,6 +2511,18 @@ module Google
         #     t.schema.integer "age", mode: :required
         #   end
         #
+        # @example Pass `BIGNUMERIC` value as a string to avoid rounding to scale 9 in the conversion from `BigDecimal`:
+        #   require "google/cloud/bigquery"
+        #
+        #   bigquery = Google::Cloud::Bigquery.new
+        #   dataset = bigquery.dataset "my_dataset"
+        #
+        #   row = {
+        #     "my_numeric" => BigDecimal("123456798.987654321"),
+        #     "my_bignumeric" => "123456798.98765432100001" # BigDecimal would be rounded, use String instead!
+        #   }
+        #   dataset.insert "my_table", row
+        #
         # @!group Data
         #
         def insert table_id, rows, insert_ids: nil, skip_invalid: nil, ignore_unknown: nil, autocreate: nil, &block
@@ -2500,11 +2615,9 @@ module Google
             create_table table_id do |tbl_updater|
               yield tbl_updater if block_given?
             end
-          # rubocop:disable Lint/HandleExceptions
           rescue Google::Cloud::AlreadyExistsError
+            # Do nothing if it already exists
           end
-          # rubocop:enable Lint/HandleExceptions
-
           sleep 60
           retry
         end
@@ -2547,7 +2660,7 @@ module Google
           return if attributes.empty?
           ensure_service!
           patch_args = Hash[attributes.map { |attr| [attr, @gapi.send(attr)] }]
-          patch_gapi = Google::Apis::BigqueryV2::Dataset.new patch_args
+          patch_gapi = Google::Apis::BigqueryV2::Dataset.new(**patch_args)
           patch_gapi.etag = etag if etag
           @gapi = service.patch_dataset dataset_id, patch_gapi
         end
@@ -2676,12 +2789,11 @@ module Google
 
         def load_local_or_uri file, updater
           job_gapi = updater.to_gapi
-          job = if local_file? file
-                  load_local file, job_gapi
-                else
-                  load_storage file, job_gapi
-                end
-          job
+          if local_file? file
+            load_local file, job_gapi
+          else
+            load_storage file, job_gapi
+          end
         end
 
         def storage_url? files
@@ -2721,6 +2833,7 @@ module Google
           ##
           # @private Create an Updater object.
           def initialize gapi
+            super()
             @updates = []
             @gapi = gapi
           end
@@ -2756,6 +2869,12 @@ module Google
             raise "not implemented in #{self.class}"
           end
 
+          ##
+          # @raise [RuntimeError] not implemented
+          def create_materialized_view(*)
+            raise "not implemented in #{self.class}"
+          end
+
           ##
           # @raise [RuntimeError] not implemented
           def table(*)

data/lib/google/cloud/bigquery/dataset/access.rb

@@ -1194,7 +1194,7 @@ module Google
             @rules.reject!(&find_by_scope_and_value(scope, value))
             # Add new rule for this role, scope, and value
             opts = { role: role, scope => value }
-            @rules << Google::Apis::BigqueryV2::Dataset::Access.new(opts)
+            @rules << Google::Apis::BigqueryV2::Dataset::Access.new(**opts)
           end
 
           # @private
@@ -1204,7 +1204,7 @@ module Google
             @rules.reject!(&find_by_scope_and_resource_ref(:routine, value))
             # Add new rule for this role, scope, and value
             opts = { routine: value }
-            @rules << Google::Apis::BigqueryV2::Dataset::Access.new(opts)
+            @rules << Google::Apis::BigqueryV2::Dataset::Access.new(**opts)
           end
 
           # @private
@@ -1215,7 +1215,7 @@ module Google
             @rules.reject!(&find_by_scope_and_resource_ref(:view, value))
             # Add new rule for this role, scope, and value
             opts = { view: value }
-            @rules << Google::Apis::BigqueryV2::Dataset::Access.new(opts)
+            @rules << Google::Apis::BigqueryV2::Dataset::Access.new(**opts)
           end
 
           # @private

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

@@ -120,12 +120,12 @@ module Google
           #     puts dataset.name
           #   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/external.rb

@@ -52,6 +52,24 @@ module Google
       #   # Retrieve the next page of results
       #   data = data.next if data.next?
       #
+      # @example Hive partitioning options:
+      #   require "google/cloud/bigquery"
+      #
+      #   bigquery = Google::Cloud::Bigquery.new
+      #
+      #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+      #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+      #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+      #     ext.hive_partitioning_mode = :auto
+      #     ext.hive_partitioning_require_partition_filter = true
+      #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+      #   end
+      #
+      #   external_data.hive_partitioning? #=> true
+      #   external_data.hive_partitioning_mode #=> "AUTO"
+      #   external_data.hive_partitioning_require_partition_filter? #=> true
+      #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+      #
       module External
         ##
         # @private New External from URLs and format
@@ -79,7 +97,8 @@ module Google
         # @private Determine source_format from inputs
         def self.source_format_for urls, format
           val = {
-            "csv" => "CSV",          "avro" => "AVRO",
+            "csv"                    => "CSV",
+            "avro"                   => "AVRO",
             "json"                   => "NEWLINE_DELIMITED_JSON",
             "newline_delimited_json" => "NEWLINE_DELIMITED_JSON",
             "sheets"                 => "GOOGLE_SHEETS",
@@ -87,7 +106,9 @@ module Google
             "datastore"              => "DATASTORE_BACKUP",
             "backup"                 => "DATASTORE_BACKUP",
             "datastore_backup"       => "DATASTORE_BACKUP",
-            "bigtable"               => "BIGTABLE"
+            "bigtable"               => "BIGTABLE",
+            "orc"                    => "ORC",
+            "parquet"                => "PARQUET"
           }[format.to_s.downcase]
           return val unless val.nil?
           Array(urls).each do |url|
@@ -110,7 +131,7 @@ module Google
           when "GOOGLE_SHEETS"          then External::SheetsSource
           when "BIGTABLE"               then External::BigtableSource
           else
-            # AVRO and DATASTORE_BACKUP
+            # AVRO, DATASTORE_BACKUP, PARQUET
             External::DataSource
           end
         end
@@ -148,6 +169,24 @@ module Google
         #   # Retrieve the next page of results
         #   data = data.next if data.next?
         #
+        # @example Hive partitioning options:
+        #   require "google/cloud/bigquery"
+        #
+        #   bigquery = Google::Cloud::Bigquery.new
+        #
+        #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+        #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+        #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+        #     ext.hive_partitioning_mode = :auto
+        #     ext.hive_partitioning_require_partition_filter = true
+        #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+        #   end
+        #
+        #   external_data.hive_partitioning? #=> true
+        #   external_data.hive_partitioning_mode #=> "AUTO"
+        #   external_data.hive_partitioning_require_partition_filter? #=> true
+        #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+        #
         class DataSource
           ##
           # @private The Google API Client object.
@@ -302,6 +341,52 @@ module Google
             @gapi.source_format == "BIGTABLE"
           end
 
+          ##
+          # Whether the data format is "ORC".
+          #
+          # @return [Boolean]
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :orc do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #   external_data.format #=> "ORC"
+          #   external_data.orc? #=> true
+          #
+          def orc?
+            @gapi.source_format == "ORC"
+          end
+
+          ##
+          # Whether the data format is "PARQUET".
+          #
+          # @return [Boolean]
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #   external_data.format #=> "PARQUET"
+          #   external_data.parquet? #=> true
+          #
+          def parquet?
+            @gapi.source_format == "PARQUET"
+          end
+
           ##
           # The fully-qualified URIs that point to your data in Google Cloud.
           # For Google Cloud Storage URIs: Each URI can contain one '*' wildcard
@@ -536,6 +621,246 @@ module Google
             @gapi.max_bad_records = new_max_bad_records
           end
 
+          ###
+          # Checks if hive partitioning options are set.
+          #
+          # Not all storage formats support hive partitioning. Requesting hive partitioning on an unsupported format
+          # will lead to an error. Currently supported types include: `avro`, `csv`, `json`, `orc` and `parquet`.
+          # If your data is stored in ORC or Parquet on Cloud Storage, see [Querying columnar formats on Cloud
+          # Storage](https://cloud.google.com/bigquery/pricing#columnar_formats_pricing).
+          #
+          # @return [Boolean] `true` when hive partitioning options are set, or `false` otherwise.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_require_partition_filter = true
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #
+          #   external_data.hive_partitioning? #=> true
+          #   external_data.hive_partitioning_mode #=> "AUTO"
+          #   external_data.hive_partitioning_require_partition_filter? #=> true
+          #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+          #
+          def hive_partitioning?
+            !@gapi.hive_partitioning_options.nil?
+          end
+
+          ###
+          # The mode of hive partitioning to use when reading data. The following modes are supported:
+          #
+          #   1. `AUTO`: automatically infer partition key name(s) and type(s).
+          #   2. `STRINGS`: automatically infer partition key name(s). All types are interpreted as strings.
+          #   3. `CUSTOM`: partition key schema is encoded in the source URI prefix.
+          #
+          # @return [String, nil] The mode of hive partitioning, or `nil` if not set.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_require_partition_filter = true
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #
+          #   external_data.hive_partitioning? #=> true
+          #   external_data.hive_partitioning_mode #=> "AUTO"
+          #   external_data.hive_partitioning_require_partition_filter? #=> true
+          #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+          #
+          def hive_partitioning_mode
+            @gapi.hive_partitioning_options.mode if hive_partitioning?
+          end
+
+          ##
+          # Sets the mode of hive partitioning to use when reading data. The following modes are supported:
+          #
+          #   1. `auto`: automatically infer partition key name(s) and type(s).
+          #   2. `strings`: automatically infer partition key name(s). All types are interpreted as strings.
+          #   3. `custom`: partition key schema is encoded in the source URI prefix.
+          #
+          # Not all storage formats support hive partitioning. Requesting hive partitioning on an unsupported format
+          # will lead to an error. Currently supported types include: `avro`, `csv`, `json`, `orc` and `parquet`.
+          # If your data is stored in ORC or Parquet on Cloud Storage, see [Querying columnar formats on Cloud
+          # Storage](https://cloud.google.com/bigquery/pricing#columnar_formats_pricing).
+          #
+          # See {#format}, {#hive_partitioning_require_partition_filter=} and {#hive_partitioning_source_uri_prefix=}.
+          #
+          # @param [String, Symbol] mode The mode of hive partitioning to use when reading data.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_require_partition_filter = true
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #
+          #   external_data.hive_partitioning? #=> true
+          #   external_data.hive_partitioning_mode #=> "AUTO"
+          #   external_data.hive_partitioning_require_partition_filter? #=> true
+          #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+          #
+          def hive_partitioning_mode= mode
+            @gapi.hive_partitioning_options ||= Google::Apis::BigqueryV2::HivePartitioningOptions.new
+            @gapi.hive_partitioning_options.mode = mode.to_s.upcase
+          end
+
+          ###
+          # Whether queries over the table using this external data source require a partition filter that can be used
+          # for partition elimination to be specified. Note that this field should only be true when creating a
+          # permanent external table or querying a temporary external table.
+          #
+          # @return [Boolean] `true` when queries over this table require a partition filter, or `false` otherwise.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_require_partition_filter = true
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #
+          #   external_data.hive_partitioning? #=> true
+          #   external_data.hive_partitioning_mode #=> "AUTO"
+          #   external_data.hive_partitioning_require_partition_filter? #=> true
+          #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+          #
+          def hive_partitioning_require_partition_filter?
+            return false unless hive_partitioning?
+            !@gapi.hive_partitioning_options.require_partition_filter.nil?
+          end
+
+          ##
+          # Sets whether queries over the table using this external data source require a partition filter
+          # that can be used for partition elimination to be specified.
+          #
+          # See {#format}, {#hive_partitioning_mode=} and {#hive_partitioning_source_uri_prefix=}.
+          #
+          # @param [Boolean] require_partition_filter `true` if a partition filter must be specified, `false` otherwise.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_require_partition_filter = true
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #
+          #   external_data.hive_partitioning? #=> true
+          #   external_data.hive_partitioning_mode #=> "AUTO"
+          #   external_data.hive_partitioning_require_partition_filter? #=> true
+          #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+          #
+          def hive_partitioning_require_partition_filter= require_partition_filter
+            @gapi.hive_partitioning_options ||= Google::Apis::BigqueryV2::HivePartitioningOptions.new
+            @gapi.hive_partitioning_options.require_partition_filter = require_partition_filter
+          end
+
+          ###
+          # The common prefix for all source uris when hive partition detection is requested. The prefix must end
+          # immediately before the partition key encoding begins. For example, consider files following this data
+          # layout:
+          #
+          # ```
+          # gs://bucket/path_to_table/dt=2019-01-01/country=BR/id=7/file.avro
+          # gs://bucket/path_to_table/dt=2018-12-31/country=CA/id=3/file.avro
+          # ```
+          #
+          # When hive partitioning is requested with either `AUTO` or `STRINGS` mode, the common prefix can be either of
+          # `gs://bucket/path_to_table` or `gs://bucket/path_to_table/` (trailing slash does not matter).
+          #
+          # @return [String, nil] The common prefix for all source uris, or `nil` if not set.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_require_partition_filter = true
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #
+          #   external_data.hive_partitioning? #=> true
+          #   external_data.hive_partitioning_mode #=> "AUTO"
+          #   external_data.hive_partitioning_require_partition_filter? #=> true
+          #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+          #
+          def hive_partitioning_source_uri_prefix
+            @gapi.hive_partitioning_options.source_uri_prefix if hive_partitioning?
+          end
+
+          ##
+          # Sets the common prefix for all source uris when hive partition detection is requested. The prefix must end
+          # immediately before the partition key encoding begins. For example, consider files following this data
+          # layout:
+          #
+          # ```
+          # gs://bucket/path_to_table/dt=2019-01-01/country=BR/id=7/file.avro
+          # gs://bucket/path_to_table/dt=2018-12-31/country=CA/id=3/file.avro
+          # ```
+          #
+          # When hive partitioning is requested with either `AUTO` or `STRINGS` mode, the common prefix can be either of
+          # `gs://bucket/path_to_table` or `gs://bucket/path_to_table/` (trailing slash does not matter).
+          #
+          # See {#format}, {#hive_partitioning_mode=} and {#hive_partitioning_require_partition_filter=}.
+          #
+          # @param [String] source_uri_prefix The common prefix for all source uris.
+          #
+          # @example
+          #   require "google/cloud/bigquery"
+          #
+          #   bigquery = Google::Cloud::Bigquery.new
+          #
+          #   gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
+          #   source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
+          #   external_data = bigquery.external gcs_uri, format: :parquet do |ext|
+          #     ext.hive_partitioning_mode = :auto
+          #     ext.hive_partitioning_require_partition_filter = true
+          #     ext.hive_partitioning_source_uri_prefix = source_uri_prefix
+          #   end
+          #
+          #   external_data.hive_partitioning? #=> true
+          #   external_data.hive_partitioning_mode #=> "AUTO"
+          #   external_data.hive_partitioning_require_partition_filter? #=> true
+          #   external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
+          #
+          def hive_partitioning_source_uri_prefix= source_uri_prefix
+            @gapi.hive_partitioning_options ||= Google::Apis::BigqueryV2::HivePartitioningOptions.new
+            @gapi.hive_partitioning_options.source_uri_prefix = source_uri_prefix
+          end
+
           ##
           # @private Google API Client object.
           def to_gapi