Class: Google::Cloud::Bigquery::Storage::V1::BigQueryRead::Client

Inherits:
Object
  • Object
show all
Includes:
Paths
Defined in:
lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb

Overview

Client for the BigQueryRead service.

BigQuery Read API.

The Read API can be used to read data from BigQuery.

Defined Under Namespace

Classes: Configuration

Class Method Summary collapse

Instance Method Summary collapse

Methods included from Paths

#project_path, #read_session_path, #read_stream_path, #table_path

Constructor Details

#initialize {|config| ... } ⇒ Client

Create a new BigQueryRead client object.

Examples:


# Create a client using the default configuration
client = ::Google::Cloud::Bigquery::Storage::V1::BigQueryRead::Client.new

# Create a client using a custom configuration
client = ::Google::Cloud::Bigquery::Storage::V1::BigQueryRead::Client.new do |config|
  config.timeout = 10.0
end

Yields:

  • (config) —

    Configure the BigQueryRead client.

Yield Parameters:



142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
 
# File 'lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb', line 142

def initialize
  # These require statements are intentionally placed here to initialize
  # the gRPC module only when it's required.
  # See https://github.com/googleapis/toolkit/issues/446
  require "gapic/grpc"
  require "google/cloud/bigquery/storage/v1/storage_services_pb"

  # Create the configuration object
  @config = Configuration.new Client.configure

  # Yield the configuration if needed
  yield @config if block_given?

  # Create credentials
  credentials = @config.credentials
  # Use self-signed JWT if the endpoint is unchanged from default,
  # but only if the default endpoint does not have a region prefix.
  enable_self_signed_jwt = @config.endpoint.nil? ||
                           (@config.endpoint == Configuration::DEFAULT_ENDPOINT &&
                           !@config.endpoint.split(".").first.include?("-"))
  credentials ||= Credentials.default scope: @config.scope,
                                      enable_self_signed_jwt: enable_self_signed_jwt
  if credentials.is_a?(::String) || credentials.is_a?(::Hash)
    credentials = Credentials.new credentials, scope: @config.scope
  end
  @quota_project_id = @config.quota_project
  @quota_project_id ||= credentials.quota_project_id if credentials.respond_to? :quota_project_id

  @big_query_read_stub = ::Gapic::ServiceStub.new(
    ::Google::Cloud::Bigquery::Storage::V1::BigQueryRead::Stub,
    credentials: credentials,
    endpoint: @config.endpoint,
    endpoint_template: DEFAULT_ENDPOINT_TEMPLATE,
    universe_domain: @config.universe_domain,
    channel_args: @config.channel_args,
    interceptors: @config.interceptors,
    channel_pool_config: @config.channel_pool,
    logger: @config.logger
  )

  @big_query_read_stub.stub_logger&.info do |entry|
    entry.set_system_name
    entry.set_service
    entry.message = "Created client for #{entry.service}"
    entry.set_credentials_fields credentials
    entry.set "customEndpoint", @config.endpoint if @config.endpoint
    entry.set "defaultTimeout", @config.timeout if @config.timeout
    entry.set "quotaProject", @quota_project_id if @quota_project_id
  end
end

Class Method Details

.configure {|config| ... } ⇒ Client::Configuration

Configure the BigQueryRead Client class.

See Configuration for a description of the configuration fields.

Examples:


# Modify the configuration for all BigQueryRead clients
::Google::Cloud::Bigquery::Storage::V1::BigQueryRead::Client.configure do |config|
  config.timeout = 10.0
end

Yields:

  • (config) —

    Configure the Client client.

Yield Parameters:

Returns:



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
 
# File 'lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb', line 65

def self.configure
  @configure ||= begin
    namespace = ["Google", "Cloud", "Bigquery", "Storage", "V1"]
    parent_config = while namespace.any?
                      parent_name = namespace.join "::"
                      parent_const = const_get parent_name
                      break parent_const.configure if parent_const.respond_to? :configure
                      namespace.pop
                    end
    default_config = Client::Configuration.new parent_config

    default_config.rpcs.create_read_session.timeout = 600.0
    default_config.rpcs.create_read_session.retry_policy = {
      initial_delay: 0.1, max_delay: 60.0, multiplier: 1.3, retry_codes: [4, 14]
    }

    default_config.rpcs.read_rows.timeout = 86_400.0
    default_config.rpcs.read_rows.retry_policy = {
      initial_delay: 0.1, max_delay: 60.0, multiplier: 1.3, retry_codes: [14]
    }

    default_config.rpcs.split_read_stream.timeout = 600.0
    default_config.rpcs.split_read_stream.retry_policy = {
      initial_delay: 0.1, max_delay: 60.0, multiplier: 1.3, retry_codes: [4, 14]
    }

    default_config
  end
  yield @configure if block_given?
  @configure
end

Instance Method Details

#configure {|config| ... } ⇒ Client::Configuration

Configure the BigQueryRead Client instance.

The configuration is set to the derived mode, meaning that values can be changed, but structural changes (adding new fields, etc.) are not allowed. Structural changes should be made on configure.

See Configuration for a description of the configuration fields.

Yields:

  • (config) —

    Configure the Client client.

Yield Parameters:

Returns:



112
113
114
115
 
# File 'lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb', line 112

def configure
  yield @config if block_given?
  @config
end

#create_read_session(request, options = nil) ⇒ ::Google::Cloud::Bigquery::Storage::V1::ReadSession #create_read_session(parent: nil, read_session: nil, max_stream_count: nil, preferred_min_stream_count: nil) ⇒ ::Google::Cloud::Bigquery::Storage::V1::ReadSession

Creates a new read session. A read session divides the contents of a BigQuery table into one or more streams, which can then be used to read data from the table. The read session also specifies properties of the data to be read, such as a list of columns or a push-down filter describing the rows to be returned.

A particular row can be read by at most one stream. When the caller has reached the end of each stream in the session, then all the data in the table has been read.

Data is assigned to each stream such that roughly the same number of rows can be read from each stream. Because the server-side unit for assigning data is collections of rows, the API does not guarantee that each stream will return the same number or rows. Additionally, the limits are enforced based on the number of pre-filtered rows, so some filters can lead to lopsided assignments.

Read sessions automatically expire 6 hours after they are created and do not require manual clean-up by the caller.

Examples:

Basic example

require "google/cloud/bigquery/storage/v1"

# Create a client object. The client can be reused for multiple calls.
client = Google::Cloud::Bigquery::Storage::V1::BigQueryRead::Client.new

# Create a request. To set request fields, pass in keyword arguments.
request = Google::Cloud::Bigquery::Storage::V1::CreateReadSessionRequest.new

# Call the create_read_session method.
result = client.create_read_session request

# The returned object is of type Google::Cloud::Bigquery::Storage::V1::ReadSession.
p result

Overloads:

  • #create_read_session(request, options = nil) ⇒ ::Google::Cloud::Bigquery::Storage::V1::ReadSession

    Pass arguments to create_read_session via a request object, either of type CreateReadSessionRequest or an equivalent Hash.

    Parameters:

    • request (::Google::Cloud::Bigquery::Storage::V1::CreateReadSessionRequest, ::Hash) —

      A request object representing the call parameters. Required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash.

    • options (::Gapic::CallOptions, ::Hash) (defaults to: nil) —

      Overrides the default settings for this call, e.g, timeout, retries, etc. Optional.

  • #create_read_session(parent: nil, read_session: nil, max_stream_count: nil, preferred_min_stream_count: nil) ⇒ ::Google::Cloud::Bigquery::Storage::V1::ReadSession

    Pass arguments to create_read_session via keyword arguments. Note that at least one keyword argument is required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash as a request object (see above).

    Parameters:

    • parent (::String) (defaults to: nil) —

      Required. The request project that owns the session, in the form of projects/{project_id}.

    • read_session (::Google::Cloud::Bigquery::Storage::V1::ReadSession, ::Hash) (defaults to: nil) —

      Required. Session to be created.

    • max_stream_count (::Integer) (defaults to: nil) —

      Max initial number of streams. If unset or zero, the server will provide a value of streams so as to produce reasonable throughput. Must be non-negative. The number of streams may be lower than the requested number, depending on the amount parallelism that is reasonable for the table. There is a default system max limit of 1,000.

      This must be greater than or equal to preferred_min_stream_count. Typically, clients should either leave this unset to let the system to determine an upper bound OR set this a size for the maximum "units of work" it can gracefully handle.

    • preferred_min_stream_count (::Integer) (defaults to: nil) —

      The minimum preferred stream count. This parameter can be used to inform the service that there is a desired lower bound on the number of streams. This is typically a target parallelism of the client (e.g. a Spark cluster with N-workers would set this to a low multiple of N to ensure good cluster utilization).

      The system will make a best effort to provide at least this number of streams, but in some cases might provide less.

Yields:

  • (response, operation) —

    Access the result along with the RPC operation

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the RPC is aborted.



289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
 
# File 'lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb', line 289

def create_read_session request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::Bigquery::Storage::V1::CreateReadSessionRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  metadata = @config.rpcs.create_read_session.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::Bigquery::Storage::V1::VERSION
  metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  header_params = {}
  if request.read_session&.table
    header_params["read_session.table"] = request.read_session.table
  end

  request_params_header = header_params.map { |k, v| "#{k}=#{v}" }.join("&")
  metadata[:"x-goog-request-params"] ||= request_params_header

  options.apply_defaults timeout:      @config.rpcs.create_read_session.timeout,
                         metadata:     metadata,
                         retry_policy: @config.rpcs.create_read_session.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @big_query_read_stub.call_rpc :create_read_session, request, options: options do |response, operation|
    yield response, operation if block_given?
  end
rescue ::GRPC::BadStatus => e
  raise ::Google::Cloud::Error.from_error(e)
end

#logger ⇒ Logger

The logger used for request/response debug logging.

Returns:

  • (Logger) 


198
199
200
 
# File 'lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb', line 198

def logger
  @big_query_read_stub.logger
end

#read_rows(request, options = nil) ⇒ ::Enumerable<::Google::Cloud::Bigquery::Storage::V1::ReadRowsResponse> #read_rows(read_stream: nil, offset: nil) ⇒ ::Enumerable<::Google::Cloud::Bigquery::Storage::V1::ReadRowsResponse>

Reads rows from the stream in the format prescribed by the ReadSession. Each response contains one or more table rows, up to a maximum of 128 MB per response; read requests which attempt to read individual rows larger than 128 MB will fail.

Each request also returns a set of stream statistics reflecting the current state of the stream.

Examples:

Basic example

require "google/cloud/bigquery/storage/v1"

# Create a client object. The client can be reused for multiple calls.
client = Google::Cloud::Bigquery::Storage::V1::BigQueryRead::Client.new

# Create a request. To set request fields, pass in keyword arguments.
request = Google::Cloud::Bigquery::Storage::V1::ReadRowsRequest.new

# Call the read_rows method to start streaming.
output = client.read_rows request

# The returned object is a streamed enumerable yielding elements of type
# ::Google::Cloud::Bigquery::Storage::V1::ReadRowsResponse
output.each do |current_response|
  p current_response
end

Overloads:

  • #read_rows(request, options = nil) ⇒ ::Enumerable<::Google::Cloud::Bigquery::Storage::V1::ReadRowsResponse>

    Pass arguments to read_rows via a request object, either of type ReadRowsRequest or an equivalent Hash.

    Parameters:

    • request (::Google::Cloud::Bigquery::Storage::V1::ReadRowsRequest, ::Hash) —

      A request object representing the call parameters. Required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash.

    • options (::Gapic::CallOptions, ::Hash) (defaults to: nil) —

      Overrides the default settings for this call, e.g, timeout, retries, etc. Optional.

  • #read_rows(read_stream: nil, offset: nil) ⇒ ::Enumerable<::Google::Cloud::Bigquery::Storage::V1::ReadRowsResponse>

    Pass arguments to read_rows via keyword arguments. Note that at least one keyword argument is required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash as a request object (see above).

    Parameters:

    • read_stream (::String) (defaults to: nil) —

      Required. Stream to read rows from.

    • offset (::Integer) (defaults to: nil) —

      The offset requested must be less than the last row read from Read. Requesting a larger offset is undefined. If not specified, start reading from offset zero.

Yields:

  • (response, operation) —

    Access the result along with the RPC operation

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the RPC is aborted.



387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
 
# File 'lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb', line 387

def read_rows request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::Bigquery::Storage::V1::ReadRowsRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  metadata = @config.rpcs.read_rows.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::Bigquery::Storage::V1::VERSION
  metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  header_params = {}
  if request.read_stream
    header_params["read_stream"] = request.read_stream
  end

  request_params_header = header_params.map { |k, v| "#{k}=#{v}" }.join("&")
  metadata[:"x-goog-request-params"] ||= request_params_header

  options.apply_defaults timeout:      @config.rpcs.read_rows.timeout,
                         metadata:     metadata,
                         retry_policy: @config.rpcs.read_rows.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @big_query_read_stub.call_rpc :read_rows, request, options: options do |response, operation|
    yield response, operation if block_given?
  end
rescue ::GRPC::BadStatus => e
  raise ::Google::Cloud::Error.from_error(e)
end

#split_read_stream(request, options = nil) ⇒ ::Google::Cloud::Bigquery::Storage::V1::SplitReadStreamResponse #split_read_stream(name: nil, fraction: nil) ⇒ ::Google::Cloud::Bigquery::Storage::V1::SplitReadStreamResponse

Splits a given ReadStream into two ReadStream objects. These ReadStream objects are referred to as the primary and the residual streams of the split. The original ReadStream can still be read from in the same manner as before. Both of the returned ReadStream objects can also be read from, and the rows returned by both child streams will be the same as the rows read from the original stream.

Moreover, the two child streams will be allocated back-to-back in the original ReadStream. Concretely, it is guaranteed that for streams original, primary, and residual, that original[0-j] = primary[0-j] and original[j-n] = residual[0-m] once the streams have been read to completion.

Examples:

Basic example

require "google/cloud/bigquery/storage/v1"

# Create a client object. The client can be reused for multiple calls.
client = Google::Cloud::Bigquery::Storage::V1::BigQueryRead::Client.new

# Create a request. To set request fields, pass in keyword arguments.
request = Google::Cloud::Bigquery::Storage::V1::SplitReadStreamRequest.new

# Call the split_read_stream method.
result = client.split_read_stream request

# The returned object is of type Google::Cloud::Bigquery::Storage::V1::SplitReadStreamResponse.
p result

Overloads:

  • #split_read_stream(request, options = nil) ⇒ ::Google::Cloud::Bigquery::Storage::V1::SplitReadStreamResponse

    Pass arguments to split_read_stream via a request object, either of type SplitReadStreamRequest or an equivalent Hash.

    Parameters:

    • request (::Google::Cloud::Bigquery::Storage::V1::SplitReadStreamRequest, ::Hash) —

      A request object representing the call parameters. Required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash.

    • options (::Gapic::CallOptions, ::Hash) (defaults to: nil) —

      Overrides the default settings for this call, e.g, timeout, retries, etc. Optional.

  • #split_read_stream(name: nil, fraction: nil) ⇒ ::Google::Cloud::Bigquery::Storage::V1::SplitReadStreamResponse

    Pass arguments to split_read_stream via keyword arguments. Note that at least one keyword argument is required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash as a request object (see above).

    Parameters:

    • name (::String) (defaults to: nil) —

      Required. Name of the stream to split.

    • fraction (::Float) (defaults to: nil) —

      A value in the range (0.0, 1.0) that specifies the fractional point at which the original stream should be split. The actual split point is evaluated on pre-filtered rows, so if a filter is provided, then there is no guarantee that the division of the rows between the new child streams will be proportional to this fractional value. Additionally, because the server-side unit for assigning data is collections of rows, this fraction will always map to a data storage boundary on the server side.

Yields:

  • (response, operation) —

    Access the result along with the RPC operation

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the RPC is aborted.



491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
 
# File 'lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb', line 491

def split_read_stream request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::Bigquery::Storage::V1::SplitReadStreamRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  metadata = @config.rpcs.split_read_stream.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::Bigquery::Storage::V1::VERSION
  metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  header_params = {}
  if request.name
    header_params["name"] = request.name
  end

  request_params_header = header_params.map { |k, v| "#{k}=#{v}" }.join("&")
  metadata[:"x-goog-request-params"] ||= request_params_header

  options.apply_defaults timeout:      @config.rpcs.split_read_stream.timeout,
                         metadata:     metadata,
                         retry_policy: @config.rpcs.split_read_stream.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @big_query_read_stub.call_rpc :split_read_stream, request, options: options do |response, operation|
    yield response, operation if block_given?
  end
rescue ::GRPC::BadStatus => e
  raise ::Google::Cloud::Error.from_error(e)
end

#universe_domain ⇒ String

The effective universe domain

Returns:

  • (String) 


122
123
124
 
# File 'lib/google/cloud/bigquery/storage/v1/big_query_read/client.rb', line 122

def universe_domain
  @big_query_read_stub.universe_domain
end