Class: Kura::Client
- Inherits:
-
Object
- Object
- Kura::Client
- Defined in:
- lib/kura/client.rb
Instance Method Summary collapse
- #_convert_tabledata_field(x, field_info) ⇒ Object
- #_convert_tabledata_row(row, schema) ⇒ Object
- #batch ⇒ Object
- #cancel_job(job, location: nil, project_id: @default_project_id, &blk) ⇒ Object
- #copy(src_dataset_id, src_table_id, dest_dataset_id, dest_table_id, mode: :truncate, src_project_id: @default_project_id, dest_project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) ⇒ Object
- #dataset(dataset_id, project_id: @default_project_id, &blk) ⇒ Object
- #datasets(project_id: @default_project_id, all: false, limit: 1000, &blk) ⇒ Object
- #delete_dataset(dataset_id, project_id: @default_project_id, delete_contents: false, &blk) ⇒ Object
- #delete_model(dataset_id, model_id, project_id: @default_project_id, &blk) ⇒ Object
- #delete_routine(dataset_id, routine_id, project_id: @default_project_id, &blk) ⇒ Object
- #delete_table(dataset_id, table_id, project_id: @default_project_id, &blk) ⇒ Object
- #extract(dataset_id, table_id, dest_uris, compression: "NONE", destination_format: "CSV", field_delimiter: ",", print_header: true, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) ⇒ Object
-
#initialize(default_project_id: nil, email_address: nil, private_key: nil, scope: nil, http_options: {timeout: 60}, default_retries: 5) ⇒ Client
constructor
A new instance of Client.
- #insert_dataset(dataset_id, project_id: @default_project_id, &blk) ⇒ Object
- #insert_job(configuration, job_id: nil, project_id: @default_project_id, media: nil, wait: nil, &blk) ⇒ Object
- #insert_routine(dataset_id, routine_id, body, project_id: @default_project_id, routine_type: "PROCEDURE", language: "SQL", arguments: [], return_type: nil, imported_libraries: [], description: nil) ⇒ Object
- #insert_table(dataset_id, table_id, project_id: @default_project_id, expiration_time: nil, friendly_name: nil, schema: nil, description: nil, query: nil, external_data_configuration: nil, use_legacy_sql: true, time_partitioning: nil, &blk) ⇒ Object
- #insert_tabledata(dataset_id, table_id, rows, project_id: @default_project_id, ignore_unknown_values: false, skip_invalid_rows: false, template_suffix: nil) ⇒ Object
- #job(job_id, location: nil, project_id: @default_project_id, fields: nil, &blk) ⇒ Object
- #job_finished?(r) ⇒ Boolean
- #jobs(project_id: @default_project_id, all_users: nil, max_creation_time: nil, min_creation_time: nil, max_results: nil, page_token: nil, parent_job_id: nil, projection: nil, state_filter: nil) ⇒ Object
- #list_tabledata(dataset_id, table_id, project_id: @default_project_id, start_index: 0, max_result: 100, page_token: nil, schema: nil, &blk) ⇒ Object
- #load(dataset_id, table_id, source_uris = nil, schema: nil, delimiter: ",", field_delimiter: delimiter, mode: :append, allow_jagged_rows: false, max_bad_records: 0, ignore_unknown_values: false, allow_quoted_newlines: false, quote: '"', skip_leading_rows: 0, source_format: "CSV", autodetect: false, range_partitioning: nil, time_partitioning: nil, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, file: nil, wait: nil, dry_run: false, &blk) ⇒ Object
- #model(dataset_id, model_id, project_id: @default_project_id, &blk) ⇒ Object
-
#models(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) ⇒ Object
Models API.
- #normalize_parameter(v) ⇒ Object
- #patch_dataset(dataset_id, project_id: @default_project_id, access: nil, description: :na, default_table_expiration_ms: :na, friendly_name: :na, &blk) ⇒ Object
- #patch_table(dataset_id, table_id, project_id: @default_project_id, expiration_time: :na, friendly_name: :na, description: :na, &blk) ⇒ Object
- #projects(limit: 1000, &blk) ⇒ Object
- #query(sql, mode: :truncate, dataset_id: nil, table_id: nil, allow_large_result: true, allow_large_results: allow_large_result, flatten_results: true, priority: "INTERACTIVE", use_query_cache: true, user_defined_function_resources: nil, use_legacy_sql: true, maximum_billing_tier: nil, maximum_bytes_billed: nil, external_data_configuration: nil, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) ⇒ Object
- #routine(dataset_id, routine_id, project_id: @default_project_id, &blk) ⇒ Object
-
#routines(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) ⇒ Object
Routines API.
- #table(dataset_id, table_id, project_id: @default_project_id, &blk) ⇒ Object
- #tables(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) ⇒ Object
- #wait_job(job, timeout = 60*10, location: nil, project_id: @default_project_id) ⇒ Object
Constructor Details
#initialize(default_project_id: nil, email_address: nil, private_key: nil, scope: nil, http_options: {timeout: 60}, default_retries: 5) ⇒ Client
12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
# File 'lib/kura/client.rb', line 12 def initialize(default_project_id: nil, email_address: nil, private_key: nil, scope: nil, http_options: {timeout: 60}, default_retries: 5) @default_project_id = default_project_id @scope = ["https://www.googleapis.com/auth/bigquery"] | (scope ? scope.is_a?(Array) ? scope : [scope] : []) @email_address = email_address @private_key = private_key if @email_address and @private_key auth = Signet::OAuth2::Client.new( token_credential_uri: "https://accounts.google.com/o/oauth2/token", audience: "https://accounts.google.com/o/oauth2/token", scope: @scope, issuer: @email_address, signing_key: @private_key) # MEMO: signet-0.6.1 depend on Farady.default_connection Faraday.default_connection..timeout = 60 auth.fetch_access_token! else auth = Google::Auth.get_application_default(@scope) auth.fetch_access_token! end Google::Apis::RequestOptions.default.retries = default_retries # to support google-api-client.gem both 0.10.x and 0.11.x # see https://github.com/google/google-api-ruby-client/blob/master/MIGRATING.md if Google::Apis::ClientOptions.default.respond_to?(:open_timeout_sec) Google::Apis::ClientOptions.default.open_timeout_sec = [:timeout] Google::Apis::ClientOptions.default.read_timeout_sec = [:timeout] Google::Apis::ClientOptions.default.send_timeout_sec = [:timeout] else Google::Apis::RequestOptions.default.open_timeout_sec = [:timeout] Google::Apis::RequestOptions.default.timeout_sec = [:timeout] end @api = Google::Apis::BigqueryV2::BigqueryService.new @api. = auth if @default_project_id.nil? @default_project_id = self.projects.first.id end end |
Instance Method Details
#_convert_tabledata_field(x, field_info) ⇒ Object
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
# File 'lib/kura/client.rb', line 250 def _convert_tabledata_field(x, field_info) if x.nil? and (field_info["mode"] == "NULLABLE" or field_info["mode"].nil?) # The tables created by New BigQuery Console could have schema without mode... return nil end case field_info["type"] when "STRING" x.to_s when "INTEGER" Integer(x) when "FLOAT" case x when "Infinity" Float::INFINITY when "-Infinity" -Float::INFINITY when "NaN" Float::NAN else Float(x) end when "BOOLEAN" x.to_s == "true" when "TIMESTAMP" Time.at(Float(x)).utc.iso8601(6) when "RECORD" _convert_tabledata_row(x, field_info["fields"]) else x end end |
#_convert_tabledata_row(row, schema) ⇒ Object
281 282 283 284 285 286 287 288 289 290 |
# File 'lib/kura/client.rb', line 281 def _convert_tabledata_row(row, schema) (row.respond_to?(:f) ? row.f : row["f"]).zip(schema).each_with_object({}) do |(v, s), tbl| v = JSON.parse(v.to_json) if s["mode"] == "REPEATED" tbl[s["name"]] = v["v"].map{|c| _convert_tabledata_field(c["v"], s) } else tbl[s["name"]] = _convert_tabledata_field(v["v"], s) end end end |
#batch ⇒ Object
77 78 79 80 81 82 83 84 85 86 |
# File 'lib/kura/client.rb', line 77 def batch @api.batch do |api| original_api, @api = @api, api begin yield ensure @api = original_api end end end |
#cancel_job(job, location: nil, project_id: @default_project_id, &blk) ⇒ Object
654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 |
# File 'lib/kura/client.rb', line 654 def cancel_job(job, location: nil, project_id: @default_project_id, &blk) case job when String jobid = job when Google::Apis::BigqueryV2::Job project_id = job.job_reference.project_id jobid = job.job_reference.job_id else raise TypeError, "Kura::Client#cancel_job accept String(job-id) or Google::Apis::BigqueryV2::Job" end if blk @api.cancel_job(project_id, jobid, location: location) do |r, e| j = (r && r.job) j.kura_api = self if j blk.call(j, e) end else @api.cancel_job(project_id, jobid, location: location).job.tap{|j| j.kura_api = self if j } end end |
#copy(src_dataset_id, src_table_id, dest_dataset_id, dest_table_id, mode: :truncate, src_project_id: @default_project_id, dest_project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) ⇒ Object
588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 |
# File 'lib/kura/client.rb', line 588 def copy(src_dataset_id, src_table_id, dest_dataset_id, dest_table_id, mode: :truncate, src_project_id: @default_project_id, dest_project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) write_disposition = mode_to_write_disposition(mode) configuration = Google::Apis::BigqueryV2::JobConfiguration.new( copy: Google::Apis::BigqueryV2::JobConfigurationTableCopy.new( destination_table: Google::Apis::BigqueryV2::TableReference.new( project_id: dest_project_id, dataset_id: dest_dataset_id, table_id: dest_table_id, ), source_table: Google::Apis::BigqueryV2::TableReference.new( project_id: src_project_id, dataset_id: src_dataset_id, table_id: src_table_id, ), write_disposition: write_disposition, ) ) if dry_run configuration.dry_run = true wait = nil end insert_job(configuration, wait: wait, job_id: job_id, project_id: job_project_id, &blk) end |
#dataset(dataset_id, project_id: @default_project_id, &blk) ⇒ Object
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
# File 'lib/kura/client.rb', line 117 def dataset(dataset_id, project_id: @default_project_id, &blk) if blk @api.get_dataset(project_id, dataset_id) do |result, err| if err.respond_to?(:status_code) and err.status_code == 404 result = nil err = nil end blk.call(result, err) end else @api.get_dataset(project_id, dataset_id) end rescue return nil if $!.respond_to?(:status_code) and $!.status_code == 404 process_error($!) end |
#datasets(project_id: @default_project_id, all: false, limit: 1000, &blk) ⇒ Object
102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
# File 'lib/kura/client.rb', line 102 def datasets(project_id: @default_project_id, all: false, limit: 1000, &blk) all = normalize_parameter(all) if blk @api.list_datasets(project_id, all: all, max_results: limit) do |result, err| result &&= (result.datasets || []) blk.call(result, err) end else result = @api.list_datasets(project_id, all: all, max_results: limit) result.datasets || [] end rescue process_error($!) end |
#delete_dataset(dataset_id, project_id: @default_project_id, delete_contents: false, &blk) ⇒ Object
149 150 151 152 153 154 155 |
# File 'lib/kura/client.rb', line 149 def delete_dataset(dataset_id, project_id: @default_project_id, delete_contents: false, &blk) delete_contents = normalize_parameter(delete_contents) @api.delete_dataset(project_id, dataset_id, delete_contents: delete_contents, &blk) rescue return nil if $!.respond_to?(:status_code) and $!.status_code == 404 process_error($!) end |
#delete_model(dataset_id, model_id, project_id: @default_project_id, &blk) ⇒ Object
755 756 757 758 759 760 |
# File 'lib/kura/client.rb', line 755 def delete_model(dataset_id, model_id, project_id: @default_project_id, &blk) @api.delete_model(project_id, dataset_id, model_id, &blk) rescue return nil if $!.respond_to?(:status_code) and $!.status_code == 404 process_error($!) end |
#delete_routine(dataset_id, routine_id, project_id: @default_project_id, &blk) ⇒ Object
793 794 795 796 797 798 |
# File 'lib/kura/client.rb', line 793 def delete_routine(dataset_id, routine_id, project_id: @default_project_id, &blk) @api.delete_routine(project_id, dataset_id, routine_id, &blk) rescue return nil if $!.respond_to?(:status_code) and $!.status_code == 404 process_error($!) end |
#delete_table(dataset_id, table_id, project_id: @default_project_id, &blk) ⇒ Object
243 244 245 246 247 248 |
# File 'lib/kura/client.rb', line 243 def delete_table(dataset_id, table_id, project_id: @default_project_id, &blk) @api.delete_table(project_id, dataset_id, table_id, &blk) rescue return nil if $!.respond_to?(:status_code) and $!.status_code == 404 process_error($!) end |
#extract(dataset_id, table_id, dest_uris, compression: "NONE", destination_format: "CSV", field_delimiter: ",", print_header: true, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) ⇒ Object
553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 |
# File 'lib/kura/client.rb', line 553 def extract(dataset_id, table_id, dest_uris, compression: "NONE", destination_format: "CSV", field_delimiter: ",", print_header: true, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) dest_uris = [ dest_uris ] if dest_uris.is_a?(String) configuration = Google::Apis::BigqueryV2::JobConfiguration.new( extract: Google::Apis::BigqueryV2::JobConfigurationExtract.new( compression: compression, destination_format: destination_format, source_table: Google::Apis::BigqueryV2::TableReference.new( project_id: project_id, dataset_id: dataset_id, table_id: table_id, ), destination_uris: dest_uris, ) ) if dry_run configuration.dry_run = true wait = nil end if destination_format == "CSV" configuration.extract.field_delimiter = field_delimiter configuration.extract.print_header = normalize_parameter(print_header) end insert_job(configuration, wait: wait, job_id: job_id, project_id: job_project_id, &blk) end |
#insert_dataset(dataset_id, project_id: @default_project_id, &blk) ⇒ Object
134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
# File 'lib/kura/client.rb', line 134 def insert_dataset(dataset_id, project_id: @default_project_id, &blk) case dataset_id when String obj = Google::Apis::BigqueryV2::Dataset.new(dataset_reference: Google::Apis::BigqueryV2::DatasetReference.new(project_id: project_id, dataset_id: dataset_id)) when Hash obj = Google::Apis::BigqueryV2::Dataset.new(**dataset_id) when Google::Apis::BigqueryV2::Dataset obj = dataset_id end @api.insert_dataset(project_id, obj, &blk) rescue process_error($!) end |
#insert_job(configuration, job_id: nil, project_id: @default_project_id, media: nil, wait: nil, &blk) ⇒ Object
367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 |
# File 'lib/kura/client.rb', line 367 def insert_job(configuration, job_id: nil, project_id: @default_project_id, media: nil, wait: nil, &blk) job_object = Google::Apis::BigqueryV2::Job.new job_object.configuration = configuration if job_id job_object.job_reference = Google::Apis::BigqueryV2::JobReference.new job_object.job_reference.project_id = project_id job_object.job_reference.job_id = job_id end if wait job = @api.insert_job(project_id, job_object, upload_source: media) job.kura_api = self wait_job(job, wait, &blk) else if blk @api.insert_job(project_id, job_object, upload_source: media) do |r, err| if r r.kura_api = self end blk.call(r, err) end else job = @api.insert_job(project_id, job_object, upload_source: media) job.kura_api = self job end end rescue process_error($!) end |
#insert_routine(dataset_id, routine_id, body, project_id: @default_project_id, routine_type: "PROCEDURE", language: "SQL", arguments: [], return_type: nil, imported_libraries: [], description: nil) ⇒ Object
800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 |
# File 'lib/kura/client.rb', line 800 def insert_routine(dataset_id, routine_id, body, project_id: @default_project_id, routine_type: "PROCEDURE", language: "SQL", arguments: [], return_type: nil, imported_libraries: [], description: nil) @api.insert_routine( project_id, dataset_id, Google::Apis::BigqueryV2::Routine.new( routine_reference: Google::Apis::BigqueryV2::RoutineReference.new( project_id: project_id, dataset_id: dataset_id, routine_id: routine_id ), arguments: arguments, definition_body: body, imported_libraries: imported_libraries, language: language, return_type: return_type, routine_type: routine_type, description: description )) end |
#insert_table(dataset_id, table_id, project_id: @default_project_id, expiration_time: nil, friendly_name: nil, schema: nil, description: nil, query: nil, external_data_configuration: nil, use_legacy_sql: true, time_partitioning: nil, &blk) ⇒ Object
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 |
# File 'lib/kura/client.rb', line 199 def insert_table(dataset_id, table_id, project_id: @default_project_id, expiration_time: nil, friendly_name: nil, schema: nil, description: nil, query: nil, external_data_configuration: nil, use_legacy_sql: true, time_partitioning: nil, &blk) if expiration_time expiration_time = (expiration_time.to_f * 1000.0).to_i end if query view = { query: query, use_legacy_sql: !!use_legacy_sql } elsif external_data_configuration elsif schema schema = { fields: normalize_schema(schema) } end table = Google::Apis::BigqueryV2::Table.new( table_reference: {project_id: project_id, dataset_id: dataset_id, table_id: table_id}, friendly_name: friendly_name, description: description, schema: schema, expiration_time: expiration_time, view: view, external_data_configuration: external_data_configuration) if time_partitioning table.time_partitioning = Google::Apis::BigqueryV2::TimePartitioning.new(**time_partitioning) end @api.insert_table(project_id, dataset_id, table, &blk) rescue process_error($!) end |
#insert_tabledata(dataset_id, table_id, rows, project_id: @default_project_id, ignore_unknown_values: false, skip_invalid_rows: false, template_suffix: nil) ⇒ Object
329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 |
# File 'lib/kura/client.rb', line 329 def insert_tabledata(dataset_id, table_id, rows, project_id: @default_project_id, ignore_unknown_values: false, skip_invalid_rows: false, template_suffix: nil) request = Google::Apis::BigqueryV2::InsertAllTableDataRequest.new request.ignore_unknown_values = ignore_unknown_values request.skip_invalid_rows = skip_invalid_rows if template_suffix request.template_suffix = template_suffix end request.rows = rows.map do |r| case r when Google::Apis::BigqueryV2::InsertAllTableDataRequest::Row r when Hash row = Google::Apis::BigqueryV2::InsertAllTableDataRequest::Row.new if r.keys.map(&:to_s) == %w{ insert_id json } row.insert_id = r[:insert_id] || r["insert_id"] row.json = r[:json] || r["json"] else row.json = r end row else raise ArgumentError, "invalid row for BigQuery tabledata.insertAll #{r.inspect}" end end @api.insert_all_table_data(project_id, dataset_id, table_id, request) rescue process_error($!) end |
#job(job_id, location: nil, project_id: @default_project_id, fields: nil, &blk) ⇒ Object
641 642 643 644 645 646 647 648 649 650 651 652 |
# File 'lib/kura/client.rb', line 641 def job(job_id, location: nil, project_id: @default_project_id, fields: nil, &blk) if blk @api.get_job(project_id, job_id, location: location, fields: fields) do |j, e| j.kura_api = self if j blk.call(j, e) end else @api.get_job(project_id, job_id, location: location, fields: fields).tap{|j| j.kura_api = self if j } end rescue process_error($!) end |
#job_finished?(r) ⇒ Boolean
675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 |
# File 'lib/kura/client.rb', line 675 def job_finished?(r) if r.status.state == "DONE" if r.status.error_result if r.status.errors raise Kura::ApiError.new(r.status.errors.map(&:reason).join(","), r.status.errors.map{|e| msg = "reason=#{e.reason} message=#{e.}" msg += " location=#{e.location}" if e.location msg += " debug_info=#{e.debug_info}" if e.debug_info msg }.join("\n")) else e = r.status.error_result msg = "reason=#{e.reason} message=#{e.}" msg += " location=#{e.location}" if e.location msg += " debug_info=#{e.debug_info}" if e.debug_info raise Kura::ApiError.new(e.reason, msg) end end return true end return false end |
#jobs(project_id: @default_project_id, all_users: nil, max_creation_time: nil, min_creation_time: nil, max_results: nil, page_token: nil, parent_job_id: nil, projection: nil, state_filter: nil) ⇒ Object
620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 |
# File 'lib/kura/client.rb', line 620 def jobs(project_id: @default_project_id, all_users: nil, max_creation_time: nil, min_creation_time: nil, max_results: nil, page_token: nil, parent_job_id: nil, projection: nil, state_filter: nil) @api.list_jobs( project_id, all_users: all_users, max_creation_time: max_creation_time, min_creation_time: min_creation_time, max_results: max_results, page_token: page_token, parent_job_id: parent_job_id, projection: projection, state_filter: state_filter) end |
#list_tabledata(dataset_id, table_id, project_id: @default_project_id, start_index: 0, max_result: 100, page_token: nil, schema: nil, &blk) ⇒ Object
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 |
# File 'lib/kura/client.rb', line 303 def list_tabledata(dataset_id, table_id, project_id: @default_project_id, start_index: 0, max_result: 100, page_token: nil, schema: nil, &blk) if schema.nil? _t = table(dataset_id, table_id, project_id: project_id) if _t schema = table(dataset_id, table_id, project_id: project_id).schema.fields else raise Kura::ApiError.new("notFound", "Not found: Table #{project_id}:#{dataset_id}.#{table_id}") end end schema = schema.map{|s| JSON.parse(s.to_json) } if blk @api.list_table_data(project_id, dataset_id, table_id, max_results: max_result, start_index: start_index, page_token: page_token) do |r, err| if r r = format_tabledata(r, schema) end blk.call(r, err) end else r = @api.list_table_data(project_id, dataset_id, table_id, max_results: max_result, start_index: start_index, page_token: page_token) format_tabledata(r, schema) end rescue process_error($!) end |
#load(dataset_id, table_id, source_uris = nil, schema: nil, delimiter: ",", field_delimiter: delimiter, mode: :append, allow_jagged_rows: false, max_bad_records: 0, ignore_unknown_values: false, allow_quoted_newlines: false, quote: '"', skip_leading_rows: 0, source_format: "CSV", autodetect: false, range_partitioning: nil, time_partitioning: nil, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, file: nil, wait: nil, dry_run: false, &blk) ⇒ Object
489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 |
# File 'lib/kura/client.rb', line 489 def load(dataset_id, table_id, source_uris=nil, schema: nil, delimiter: ",", field_delimiter: delimiter, mode: :append, allow_jagged_rows: false, max_bad_records: 0, ignore_unknown_values: false, allow_quoted_newlines: false, quote: '"', skip_leading_rows: 0, source_format: "CSV", autodetect: false, range_partitioning: nil, time_partitioning: nil, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, file: nil, wait: nil, dry_run: false, &blk) write_disposition = mode_to_write_disposition(mode) source_uris = [source_uris] if source_uris.is_a?(String) case range_partitioning when Hash range_partitioning = Google::Apis::BigqueryV2::RangePartitioning.new(**range_partitioning) end case time_partitioning when Hash time_partitioning = Google::Apis::BigqueryV2::TimePartitioning.new(**time_partitioning) end configuration = Google::Apis::BigqueryV2::JobConfiguration.new( load: Google::Apis::BigqueryV2::JobConfigurationLoad.new( destination_table: Google::Apis::BigqueryV2::TableReference.new( project_id: project_id, dataset_id: dataset_id, table_id: table_id, ), write_disposition: write_disposition, allow_jagged_rows: normalize_parameter(allow_jagged_rows), max_bad_records: max_bad_records, ignore_unknown_values: normalize_parameter(ignore_unknown_values), source_format: source_format, range_partitioning: range_partitioning, time_partitioning: time_partitioning, ) ) if dry_run configuration.dry_run = true wait = nil end if schema configuration.load.schema = Google::Apis::BigqueryV2::TableSchema.new(fields: normalize_schema(schema)) end if source_format == "CSV" configuration.load.field_delimiter = field_delimiter configuration.load.allow_quoted_newlines = normalize_parameter(allow_quoted_newlines) configuration.load.quote = quote configuration.load.skip_leading_rows = skip_leading_rows configuration.load.autodetect = autodetect elsif source_format == "NEWLINE_DELIMITED_JSON" configuration.load.autodetect = autodetect end unless file configuration.load.source_uris = source_uris end insert_job(configuration, media: file, wait: wait, job_id: job_id, project_id: job_project_id, &blk) end |
#model(dataset_id, model_id, project_id: @default_project_id, &blk) ⇒ Object
738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 |
# File 'lib/kura/client.rb', line 738 def model(dataset_id, model_id, project_id: @default_project_id, &blk) if blk @api.get_model(project_id, dataset_id, model_id) do |result, err| if err.respond_to?(:status_code) and err.status_code == 404 result = nil err = nil end blk.call(result, err) end else @api.get_model(project_id, dataset_id, model_id) end rescue return nil if $!.respond_to?(:status_code) and $!.status_code == 404 process_error($!) end |
#models(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) ⇒ Object
Models API
725 726 727 728 729 730 731 732 733 734 735 736 |
# File 'lib/kura/client.rb', line 725 def models(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) if blk @api.list_models(project_id, dataset_id, max_results: limit, page_token: page_token) do |result, err| result &&= (result.models || []) blk.call(result, err) end else @api.list_models(project_id, dataset_id, max_results: limit, page_token: page_token) end rescue process_error($!) end |
#normalize_parameter(v) ⇒ Object
50 51 52 53 54 55 56 57 |
# File 'lib/kura/client.rb', line 50 def normalize_parameter(v) case v when nil nil else v.to_s end end |
#patch_dataset(dataset_id, project_id: @default_project_id, access: nil, description: :na, default_table_expiration_ms: :na, friendly_name: :na, &blk) ⇒ Object
157 158 159 160 161 162 163 164 165 166 |
# File 'lib/kura/client.rb', line 157 def patch_dataset(dataset_id, project_id: @default_project_id, access: nil, description: :na, default_table_expiration_ms: :na, friendly_name: :na, &blk) obj = Google::Apis::BigqueryV2::Dataset.new(dataset_reference: Google::Apis::BigqueryV2::DatasetReference.new(project_id: project_id, dataset_id: dataset_id)) obj.access = access if access obj.default_table_expiration_ms = default_table_expiration_ms if default_table_expiration_ms != :na obj.description = description if description != :na obj.friendly_name = friendly_name if friendly_name != :na @api.patch_dataset(project_id, dataset_id, obj, &blk) rescue process_error($!) end |
#patch_table(dataset_id, table_id, project_id: @default_project_id, expiration_time: :na, friendly_name: :na, description: :na, &blk) ⇒ Object
230 231 232 233 234 235 236 237 238 239 240 241 |
# File 'lib/kura/client.rb', line 230 def patch_table(dataset_id, table_id, project_id: @default_project_id, expiration_time: :na, friendly_name: :na, description: :na, &blk) if expiration_time != :na and not(expiration_time.nil?) expiration_time = (expiration_time.to_f * 1000.0).to_i end table = Google::Apis::BigqueryV2::Table.new(table_reference: {project_id: project_id, dataset_id: dataset_id, table_id: table_id}) table.friendly_name = friendly_name if friendly_name != :na table.description = description if description != :na table.expiration_time = expiration_time if expiration_time != :na @api.patch_table(project_id, dataset_id, table_id, table, &blk) rescue process_error($!) end |
#projects(limit: 1000, &blk) ⇒ Object
88 89 90 91 92 93 94 95 96 97 98 99 100 |
# File 'lib/kura/client.rb', line 88 def projects(limit: 1000, &blk) if blk @api.list_projects(max_results: limit) do |result, err| result &&= result.projects blk.call(result, err) end else result = @api.list_projects(max_results: limit) result.projects end rescue process_error($!) end |
#query(sql, mode: :truncate, dataset_id: nil, table_id: nil, allow_large_result: true, allow_large_results: allow_large_result, flatten_results: true, priority: "INTERACTIVE", use_query_cache: true, user_defined_function_resources: nil, use_legacy_sql: true, maximum_billing_tier: nil, maximum_bytes_billed: nil, external_data_configuration: nil, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) ⇒ Object
397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 |
# File 'lib/kura/client.rb', line 397 def query(sql, mode: :truncate, dataset_id: nil, table_id: nil, allow_large_result: true, # for backward compatibility allow_large_results: allow_large_result, flatten_results: true, priority: "INTERACTIVE", use_query_cache: true, user_defined_function_resources: nil, use_legacy_sql: true, maximum_billing_tier: nil, maximum_bytes_billed: nil, external_data_configuration: nil, project_id: @default_project_id, job_project_id: @default_project_id, job_id: nil, wait: nil, dry_run: false, &blk) configuration = Google::Apis::BigqueryV2::JobConfiguration.new( query: Google::Apis::BigqueryV2::JobConfigurationQuery.new( query: sql, allow_large_results: normalize_parameter(allow_large_results), flatten_results: normalize_parameter(flatten_results), priority: priority, use_query_cache: normalize_parameter(use_query_cache), use_legacy_sql: use_legacy_sql, ) ) if mode configuration.query.write_disposition = mode_to_write_disposition(mode) end if dry_run configuration.dry_run = true wait = nil end if maximum_billing_tier configuration.query.maximum_billing_tier = maximum_billing_tier end if maximum_bytes_billed configuration.query.maximum_bytes_billed = maximum_bytes_billed end if dataset_id and table_id configuration.query.destination_table = Google::Apis::BigqueryV2::TableReference.new(project_id: project_id, dataset_id: dataset_id, table_id: table_id) end if user_defined_function_resources configuration.query.user_defined_function_resources = Array(user_defined_function_resources).map do |r| r = r.to_s if r.start_with?("gs://") Google::Apis::BigqueryV2::UserDefinedFunctionResource.new(resource_uri: r) else Google::Apis::BigqueryV2::UserDefinedFunctionResource.new(inline_code: r) end end end if external_data_configuration configuration.query.table_definitions = external_data_configuration end insert_job(configuration, wait: wait, job_id: job_id, project_id: job_project_id, &blk) end |
#routine(dataset_id, routine_id, project_id: @default_project_id, &blk) ⇒ Object
776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 |
# File 'lib/kura/client.rb', line 776 def routine(dataset_id, routine_id, project_id: @default_project_id, &blk) if blk @api.get_routine(project_id, dataset_id, routine_id) do |result, err| if err.respond_to?(:status_code) and err.status_code == 404 result = nil err = nil end blk.call(result, err) end else @api.get_routine(project_id, dataset_id, routine_id) end rescue return nil if $!.respond_to?(:status_code) and $!.status_code == 404 process_error($!) end |
#routines(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) ⇒ Object
Routines API
763 764 765 766 767 768 769 770 771 772 773 774 |
# File 'lib/kura/client.rb', line 763 def routines(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) if blk @api.list_routines(project_id, dataset_id, max_results: limit, page_token: page_token) do |result, err| result &&= (result.routines || []) blk.call(result, err) end else @api.list_routines(project_id, dataset_id, max_results: limit, page_token: page_token) end rescue process_error($!) end |
#table(dataset_id, table_id, project_id: @default_project_id, &blk) ⇒ Object
182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
# File 'lib/kura/client.rb', line 182 def table(dataset_id, table_id, project_id: @default_project_id, &blk) if blk @api.get_table(project_id, dataset_id, table_id) do |result, err| if err.respond_to?(:status_code) and err.status_code == 404 result = nil err = nil end blk.call(result, err) end else @api.get_table(project_id, dataset_id, table_id) end rescue return nil if $!.respond_to?(:status_code) and $!.status_code == 404 process_error($!) end |
#tables(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) ⇒ Object
168 169 170 171 172 173 174 175 176 177 178 179 180 |
# File 'lib/kura/client.rb', line 168 def tables(dataset_id, project_id: @default_project_id, limit: 1000, page_token: nil, &blk) if blk @api.list_tables(project_id, dataset_id, max_results: limit, page_token: page_token) do |result, err| result &&= (result.tables || []) blk.call(result, err) end else result = @api.list_tables(project_id, dataset_id, max_results: limit, page_token: page_token) result.tables || [] end rescue process_error($!) end |
#wait_job(job, timeout = 60*10, location: nil, project_id: @default_project_id) ⇒ Object
699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 |
# File 'lib/kura/client.rb', line 699 def wait_job(job, timeout=60*10, location: nil, project_id: @default_project_id) case job when String job_id = job when Google::Apis::BigqueryV2::Job project_id = job.job_reference.project_id job_id = job.job_reference.job_id location = job.job_reference.location else raise TypeError, "Kura::Client#wait_job accept String(job-id) or Google::Apis::BigqueryV2::Job" end expire = Time.now + timeout while expire > Time.now j = job(job_id, project_id: project_id, location: location) if job_finished?(j) return j end if block_given? yield j end sleep 1 end raise Kura::TimeoutError, "wait job timeout" end |