Types for BigQuery Storage API Client#
-
class
google.cloud.bigquery_storage_v1beta1.types.
ArrowRecordBatch
# Arrow RecordBatch.
-
serialized_record_batch
# IPC serialized Arrow RecordBatch.
-
row_count
# The count of rows in the returning block.
-
row_count
Field google.cloud.bigquery.storage.v1beta1.ArrowRecordBatch.row_count
-
serialized_record_batch
Field google.cloud.bigquery.storage.v1beta1.ArrowRecordBatch.serialized_record_batch
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
ArrowSchema
# Arrow schema.
-
serialized_schema
# IPC serialized Arrow schema.
-
serialized_schema
Field google.cloud.bigquery.storage.v1beta1.ArrowSchema.serialized_schema
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
AvroRows
# Avro rows.
-
serialized_binary_rows
# Binary serialized rows in a block.
-
row_count
# The count of rows in the returning block.
-
row_count
Field google.cloud.bigquery.storage.v1beta1.AvroRows.row_count
-
serialized_binary_rows
Field google.cloud.bigquery.storage.v1beta1.AvroRows.serialized_binary_rows
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
AvroSchema
# Avro schema.
-
schema
# Json serialized schema, as described at https://avro.apache.org/docs/1.8.1/spec.html
-
schema
Field google.cloud.bigquery.storage.v1beta1.AvroSchema.schema
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
BatchCreateReadSessionStreamsRequest
# Information needed to request additional streams for an established read session.
-
session
# Required. Must be a non-expired session obtained from a call to CreateReadSession. Only the name field needs to be set.
-
requested_streams
# Required. Number of new streams requested. Must be positive. Number of added streams may be less than this, see CreateReadSessionRequest for more information.
-
requested_streams
Field google.cloud.bigquery.storage.v1beta1.BatchCreateReadSessionStreamsRequest.requested_streams
-
session
Field google.cloud.bigquery.storage.v1beta1.BatchCreateReadSessionStreamsRequest.session
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
BatchCreateReadSessionStreamsResponse
# The response from
BatchCreateReadSessionStreams
returns the stream identifiers for the newly created streams.-
streams
# Newly added streams.
-
streams
Field google.cloud.bigquery.storage.v1beta1.BatchCreateReadSessionStreamsResponse.streams
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
CreateReadSessionRequest
# Creates a new read session, which may include additional options such as requested parallelism, projection filters and constraints.
-
table_reference
# Required. Reference to the table to read.
-
parent
# Required. String of the form
projects/{project_id}
indicating the project this ReadSession is associated with. This is the project that will be billed for usage.
-
table_modifiers
# Optional. Any modifiers to the Table (e.g. snapshot timestamp).
-
requested_streams
# Optional. Initial number of streams. If unset or 0, we 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 and the maximum amount of parallelism allowed by the system. Streams must be read starting from offset 0.
-
read_options
# Optional. Read options for this session (e.g. column selection, filters).
-
format
# Data output format. Currently default to Avro.
-
sharding_strategy
# The strategy to use for distributing data among multiple streams. Currently defaults to liquid sharding.
-
format
Field google.cloud.bigquery.storage.v1beta1.CreateReadSessionRequest.format
-
parent
Field google.cloud.bigquery.storage.v1beta1.CreateReadSessionRequest.parent
-
read_options
Field google.cloud.bigquery.storage.v1beta1.CreateReadSessionRequest.read_options
-
requested_streams
Field google.cloud.bigquery.storage.v1beta1.CreateReadSessionRequest.requested_streams
-
sharding_strategy
Field google.cloud.bigquery.storage.v1beta1.CreateReadSessionRequest.sharding_strategy
-
table_modifiers
Field google.cloud.bigquery.storage.v1beta1.CreateReadSessionRequest.table_modifiers
-
table_reference
Field google.cloud.bigquery.storage.v1beta1.CreateReadSessionRequest.table_reference
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
Empty
#
-
class
google.cloud.bigquery_storage_v1beta1.types.
FinalizeStreamRequest
# Request information for invoking
FinalizeStream
.-
stream
# Stream to finalize.
-
stream
Field google.cloud.bigquery.storage.v1beta1.FinalizeStreamRequest.stream
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
ReadRowsRequest
# Requesting row data via
ReadRows
must provide Stream position information.-
read_position
# Required. Identifier of the position in the stream to start reading from. The offset requested must be less than the last row read from ReadRows. Requesting a larger offset is undefined.
-
read_position
Field google.cloud.bigquery.storage.v1beta1.ReadRowsRequest.read_position
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
ReadRowsResponse
# Response from calling
ReadRows
may include row data, progress and throttling information.-
rows
# Row data is returned in format specified during session creation.
-
avro_rows
# Serialized row data in AVRO format.
-
arrow_record_batch
# Serialized row data in Arrow RecordBatch format.
-
row_count
# Number of serialized rows in the rows block. This value is recorded here, in addition to the row_count values in the output-specific messages in
rows
, so that code which needs to record progress through the stream can do so in an output format-independent way.
-
status
# Estimated stream statistics.
-
throttle_status
# Throttling status. If unset, the latest response still describes the current throttling status.
-
arrow_record_batch
Field google.cloud.bigquery.storage.v1beta1.ReadRowsResponse.arrow_record_batch
-
avro_rows
Field google.cloud.bigquery.storage.v1beta1.ReadRowsResponse.avro_rows
-
row_count
Field google.cloud.bigquery.storage.v1beta1.ReadRowsResponse.row_count
-
status
Field google.cloud.bigquery.storage.v1beta1.ReadRowsResponse.status
-
throttle_status
Field google.cloud.bigquery.storage.v1beta1.ReadRowsResponse.throttle_status
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
ReadSession
# Information returned from a
CreateReadSession
request.-
name
# Unique identifier for the session, in the form
projects/{pro ject_id}/locations/{location}/sessions/{session_id}
.
-
expire_time
# Time at which the session becomes invalid. After this time, subsequent requests to read this Session will return errors.
-
schema
# The schema for the read. If read_options.selected_fields is set, the schema may be different from the table schema as it will only contain the selected fields.
-
avro_schema
# Avro schema.
-
arrow_schema
# Arrow schema.
-
streams
# Streams associated with this session.
-
table_reference
# Table that this ReadSession is reading from.
-
table_modifiers
# Any modifiers which are applied when reading from the specified table.
-
sharding_strategy
# The strategy to use for distributing data among the streams.
-
arrow_schema
Field google.cloud.bigquery.storage.v1beta1.ReadSession.arrow_schema
-
avro_schema
Field google.cloud.bigquery.storage.v1beta1.ReadSession.avro_schema
-
expire_time
Field google.cloud.bigquery.storage.v1beta1.ReadSession.expire_time
-
name
Field google.cloud.bigquery.storage.v1beta1.ReadSession.name
-
sharding_strategy
Field google.cloud.bigquery.storage.v1beta1.ReadSession.sharding_strategy
-
streams
Field google.cloud.bigquery.storage.v1beta1.ReadSession.streams
-
table_modifiers
Field google.cloud.bigquery.storage.v1beta1.ReadSession.table_modifiers
-
table_reference
Field google.cloud.bigquery.storage.v1beta1.ReadSession.table_reference
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
SplitReadStreamRequest
# Request information for
SplitReadStream
.-
original_stream
# Stream to split.
-
fraction
# 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 to a data storage boundary on the server side.
-
fraction
Field google.cloud.bigquery.storage.v1beta1.SplitReadStreamRequest.fraction
-
original_stream
Field google.cloud.bigquery.storage.v1beta1.SplitReadStreamRequest.original_stream
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
SplitReadStreamResponse
# Response from
SplitReadStream
.-
primary_stream
# Primary stream, which contains the beginning portion of |original_stream|. An empty value indicates that the original stream can no longer be split.
-
remainder_stream
# Remainder stream, which contains the tail of |original_stream|. An empty value indicates that the original stream can no longer be split.
-
primary_stream
Field google.cloud.bigquery.storage.v1beta1.SplitReadStreamResponse.primary_stream
-
remainder_stream
Field google.cloud.bigquery.storage.v1beta1.SplitReadStreamResponse.remainder_stream
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
Stream
# Information about a single data stream within a read session.
-
name
# Name of the stream, in the form
projects/{project_id}/locati ons/{location}/streams/{stream_id}
.
-
name
Field google.cloud.bigquery.storage.v1beta1.Stream.name
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
StreamPosition
# Expresses a point within a given stream using an offset position.
-
stream
# Identifier for a given Stream.
-
offset
# Position in the stream.
-
offset
Field google.cloud.bigquery.storage.v1beta1.StreamPosition.offset
-
stream
Field google.cloud.bigquery.storage.v1beta1.StreamPosition.stream
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
StreamStatus
# Progress information for a given Stream.
-
estimated_row_count
# Number of estimated rows in the current stream. May change over time as different readers in the stream progress at rates which are relatively fast or slow.
-
fraction_consumed
# A value in the range [0.0, 1.0] that represents the fraction of rows assigned to this stream that have been processed by the server. In the presence of read filters, the server may process more rows than it returns, so this value reflects progress through the pre-filtering rows. This value is only populated for sessions created through the BALANCED sharding strategy.
-
is_splittable
# Whether this stream can be split. For sessions that use the LIQUID sharding strategy, this value is always false. For BALANCED sessions, this value is false when enough data have been read such that no more splits are possible at that point or beyond. For small tables or streams that are the result of a chain of splits, this value may never be true.
-
estimated_row_count
Field google.cloud.bigquery.storage.v1beta1.StreamStatus.estimated_row_count
-
fraction_consumed
Field google.cloud.bigquery.storage.v1beta1.StreamStatus.fraction_consumed
-
is_splittable
Field google.cloud.bigquery.storage.v1beta1.StreamStatus.is_splittable
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
TableModifiers
# All fields in this message optional.
-
snapshot_time
# The snapshot time of the table. If not set, interpreted as now.
-
snapshot_time
Field google.cloud.bigquery.storage.v1beta1.TableModifiers.snapshot_time
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
TableReadOptions
# Options dictating how we read a table.
-
selected_fields
# Optional. Names of the fields in the table that should be read. If empty, all fields will be read. If the specified field is a nested field, all the sub-fields in the field will be selected. The output field order is unrelated to the order of fields in selected_fields.
-
row_restriction
# Optional. SQL text filtering statement, similar to a WHERE clause in a query. Currently, only a single predicate that is a comparison between a column and a constant value is supported. Aggregates are not supported. Examples: “int_field > 5” “date_field = CAST(‘2014-9-27’ as DATE)” “nullable_field is not NULL” “st_equals(geo_field, st_geofromtext(“POINT(2, 2)”))” “numeric_field BETWEEN 1.0 AND 5.0”
-
row_restriction
Field google.cloud.bigquery.storage.v1beta1.TableReadOptions.row_restriction
-
selected_fields
Field google.cloud.bigquery.storage.v1beta1.TableReadOptions.selected_fields
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
TableReference
# Table reference that includes just the 3 strings needed to identify a table.
-
project_id
# The assigned project ID of the project.
-
dataset_id
# The ID of the dataset in the above project.
-
table_id
# The ID of the table in the above dataset.
-
dataset_id
Field google.cloud.bigquery.storage.v1beta1.TableReference.dataset_id
-
project_id
Field google.cloud.bigquery.storage.v1beta1.TableReference.project_id
-
table_id
Field google.cloud.bigquery.storage.v1beta1.TableReference.table_id
-
-
class
google.cloud.bigquery_storage_v1beta1.types.
ThrottleStatus
# Information on if the current connection is being throttled.
-
throttle_percent
# How much this connection is being throttled. 0 is no throttling, 100 is completely throttled.
-
throttle_percent
Field google.cloud.bigquery.storage.v1beta1.ThrottleStatus.throttle_percent
-