feat: updates for v1beta2 storage API

- Updated comments on BatchCommitWriteStreams
- Added new support Bigquery types BIGNUMERIC and INTERVAL to TableSchema
- Added read rows schema in ReadRowsResponse
- Misc comment updates

Committer: @yirutang
PiperOrigin-RevId: 366811078

google/cloud/bigquery/storage/v1beta2/arrow.proto

@@ -1,4 +1,4 @@
-// Copyright 2020 Google LLC
+// Copyright 2021 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.

google/cloud/bigquery/storage/v1beta2/avro.proto

@@ -1,4 +1,4 @@
-// Copyright 2020 Google LLC
+// Copyright 2021 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.

google/cloud/bigquery/storage/v1beta2/protobuf.proto

@@ -1,4 +1,4 @@
-// Copyright 2020 Google LLC
+// Copyright 2021 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -23,7 +23,7 @@ option java_multiple_files = true;
 option java_outer_classname = "ProtoBufProto";
 option java_package = "com.google.cloud.bigquery.storage.v1beta2";
 
-// Protobuf schema is an API presentation the proto buffer schema.
+// ProtoSchema describes the schema of the serialized protocol buffer data rows.
 message ProtoSchema {
   // Descriptor for input message. The descriptor has to be self contained,
   // including all the nested types, excepted for proto buffer well known types
@@ -31,7 +31,6 @@ message ProtoSchema {
   google.protobuf.DescriptorProto proto_descriptor = 1;
 }
 
-// Protobuf rows.
 message ProtoRows {
   // A sequence of rows serialized as a Protocol Buffer.
   //

google/cloud/bigquery/storage/v1beta2/storage.proto

@@ -1,4 +1,4 @@
-// Copyright 2020 Google LLC
+// Copyright 2021 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -71,8 +71,7 @@ service BigQueryRead {
       post: "/v1beta2/{read_session.table=projects/*/datasets/*/tables/*}"
       body: "*"
     };
-    option (google.api.method_signature) =
-        "parent,read_session,max_stream_count";
+    option (google.api.method_signature) = "parent,read_session,max_stream_count";
   }
 
   // Reads rows from the stream in the format prescribed by the ReadSession.
@@ -101,8 +100,7 @@ service BigQueryRead {
   // 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.
-  rpc SplitReadStream(SplitReadStreamRequest)
-      returns (SplitReadStreamResponse) {
+  rpc SplitReadStream(SplitReadStreamRequest) returns (SplitReadStreamResponse) {
     option (google.api.http) = {
       get: "/v1beta2/{name=projects/*/locations/*/sessions/*/streams/*}"
     };
@@ -171,8 +169,7 @@ service BigQueryWrite {
 
   // Finalize a write stream so that no new data can be appended to the
   // stream. Finalize is not supported on the '_default' stream.
-  rpc FinalizeWriteStream(FinalizeWriteStreamRequest)
-      returns (FinalizeWriteStreamResponse) {
+  rpc FinalizeWriteStream(FinalizeWriteStreamRequest) returns (FinalizeWriteStreamResponse) {
     option (google.api.http) = {
       post: "/v1beta2/{name=projects/*/datasets/*/tables/*/streams/*}"
       body: "*"
@@ -185,8 +182,7 @@ service BigQueryWrite {
   // Streams must be finalized before commit and cannot be committed multiple
   // times. Once a stream is committed, data in the stream becomes available
   // for read operations.
-  rpc BatchCommitWriteStreams(BatchCommitWriteStreamsRequest)
-      returns (BatchCommitWriteStreamsResponse) {
+  rpc BatchCommitWriteStreams(BatchCommitWriteStreamsRequest) returns (BatchCommitWriteStreamsResponse) {
     option (google.api.http) = {
       get: "/v1beta2/{parent=projects/*/datasets/*/tables/*}"
     };
@@ -303,6 +299,19 @@ message ReadRowsResponse {
   // Throttling state. If unset, the latest response still describes
   // the current throttling status.
   ThrottleState throttle_state = 5;
+
+  // 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. This schema is equivelant to the one returned by
+  // CreateSession. This field is only populated in the first ReadRowsResponse
+  // RPC.
+  oneof schema {
+    // Output only. Avro schema.
+    AvroSchema avro_schema = 7 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+    // Output only. Arrow schema.
+    ArrowSchema arrow_schema = 8 [(google.api.field_behavior) = OUTPUT_ONLY];
+  }
 }
 
 // Request message for `SplitReadStream`.
@@ -342,7 +351,9 @@ message CreateWriteStreamRequest {
   // of `projects/{project}/datasets/{dataset}/tables/{table}`.
   string parent = 1 [
     (google.api.field_behavior) = REQUIRED,
-    (google.api.resource_reference) = { type: "bigquery.googleapis.com/Table" }
+    (google.api.resource_reference) = {
+      type: "bigquery.googleapis.com/Table"
+    }
   ];
 
   // Required. Stream to be created.
@@ -360,9 +371,9 @@ message AppendRowsRequest {
     ProtoRows rows = 2;
   }
 
-  // Required. The stream that is the target of the append operation. This value
-  // must be specified for the initial request. If subsequent requests specify
-  // the stream name, it must equal to the value provided in the first request.
+  // Required. The stream that is the target of the append operation. This value must be
+  // specified for the initial request. If subsequent requests specify the
+  // stream name, it must equal to the value provided in the first request.
   // To write to the _default stream, populate this field with a string in the
   // format `projects/{project}/datasets/{dataset}/tables/{table}/_default`.
   string write_stream = 1 [
@@ -394,7 +405,7 @@ message AppendRowsRequest {
 
 // Response message for `AppendRows`.
 message AppendRowsResponse {
-  // A success append result.
+  // AppendResult is returned for successful append requests.
   message AppendResult {
     // The row offset at which the last append occurred. The offset will not be
     // set if appending using default streams.
@@ -405,25 +416,32 @@ message AppendRowsResponse {
     // Result if the append is successful.
     AppendResult append_result = 1;
 
-    // Error in case of request failed. If set, it means rows are not accepted
-    // into the system. Users can retry or continue with other requests within
-    // the same connection.
-    // ALREADY_EXISTS: happens when offset is specified, it means the entire
-    //   request is already appended, it is safe to ignore this error.
-    // OUT_OF_RANGE: happens when offset is specified, it means the specified
-    //   offset is beyond the end of the stream.
-    // INVALID_ARGUMENT: error caused by malformed request or data.
-    // RESOURCE_EXHAUSTED: request rejected due to throttling. Only happens when
-    //   append without offset.
-    // ABORTED: request processing is aborted because of prior failures, request
-    //   can be retried if previous failure is fixed.
-    // INTERNAL: server side errors that can be retried.
+    // Error returned when problems were encountered.  If present,
+    // it indicates rows were not accepted into the system.
+    // Users can retry or continue with other append requests within the
+    // same connection.
+    //
+    // Additional information about error signalling:
+    //
+    // ALREADY_EXISTS: Happens when an append specified an offset, and the
+    // backend already has received data at this offset.  Typically encountered
+    // in retry scenarios, and can be ignored.
+    //
+    // OUT_OF_RANGE: Returned when the specified offset in the stream is beyond
+    // the current end of the stream.
+    //
+    // INVALID_ARGUMENT: Indicates a malformed request or data.
+    //
+    // ABORTED: Request processing is aborted because of prior failures.  The
+    // request can be retried if previous failure is addressed.
+    //
+    // INTERNAL: Indicates server side error(s) that can be retried.
     google.rpc.Status error = 2;
   }
 
   // If backend detects a schema update, pass it to user so that user can
-  // use it to input new type of message. It will be empty when there is no
-  // schema updates.
+  // use it to input new type of message. It will be empty when no schema
+  // updates have occurred.
   TableSchema updated_schema = 3;
 }
 
@@ -441,9 +459,11 @@ message GetWriteStreamRequest {
 
 // Request message for `BatchCommitWriteStreams`.
 message BatchCommitWriteStreamsRequest {
-  // Required. Parent table that all the streams should belong to, in the form
-  // of `projects/{project}/datasets/{dataset}/tables/{table}`.
-  string parent = 1 [(google.api.field_behavior) = REQUIRED];
+  // Required. Parent table that all the streams should belong to, in the form of
+  // `projects/{project}/datasets/{dataset}/tables/{table}`.
+  string parent = 1 [
+    (google.api.field_behavior) = REQUIRED
+  ];
 
   // Required. The group of streams that will be committed atomically.
   repeated string write_streams = 2 [(google.api.field_behavior) = REQUIRED];
@@ -452,11 +472,15 @@ message BatchCommitWriteStreamsRequest {
 // Response message for `BatchCommitWriteStreams`.
 message BatchCommitWriteStreamsResponse {
   // The time at which streams were committed in microseconds granularity.
-  // This field will only exist when there is no stream errors.
+  // This field will only exist when there are no stream errors.
+  // **Note** if this field is not set, it means the commit was not successful.
   google.protobuf.Timestamp commit_time = 1;
 
   // Stream level error if commit failed. Only streams with error will be in
   // the list.
+  // If empty, there is no error and all streams are committed successfully.
+  // If non empty, certain streams have errors and ZERO stream is committed due
+  // to atomicity guarantee.
   repeated StorageError stream_errors = 2;
 }
 
@@ -500,8 +524,9 @@ message FlushRowsResponse {
 }
 
 // Structured custom BigQuery Storage error message. The error can be attached
-// as error details in the returned rpc Status. User can use the info to process
-// errors in a structural way, rather than having to parse error messages.
+// as error details in the returned rpc Status. In particular, the use of error
+// codes allows more structured error handling, and reduces the need to evaluate
+// unstructured error text strings.
 message StorageError {
   // Error code for `StorageError`.
   enum StorageErrorCode {
@@ -522,9 +547,12 @@ message StorageError {
     INVALID_STREAM_TYPE = 4;
 
     // Invalid Stream state.
-    // For example, you try to commit a stream that is not fianlized or is
+    // For example, you try to commit a stream that is not finalized or is
     // garbaged.
     INVALID_STREAM_STATE = 5;
+
+    // Stream is finalized.
+    STREAM_FINALIZED = 6;
   }
 
   // BigQuery Storage specific error code.

google/cloud/bigquery/storage/v1beta2/stream.proto

@@ -1,4 +1,4 @@
-// Copyright 2020 Google LLC
+// Copyright 2021 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -74,6 +74,8 @@ message ReadSession {
     //           "nullable_field is not NULL"
     //           "st_equals(geo_field, st_geofromtext("POINT(2, 2)"))"
     //           "numeric_field BETWEEN 1.0 AND 5.0"
+    //
+    // Restricted to a maximum length for 1 MB.
     string row_restriction = 2;
 
     // Optional. Options specific to the Apache Arrow output format.

google/cloud/bigquery/storage/v1beta2/table.proto

@@ -1,4 +1,4 @@
-// Copyright 2020 Google LLC
+// Copyright 2021 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -70,6 +70,12 @@ message TableFieldSchema {
 
     // Numeric value
     NUMERIC = 12;
+
+    // BigNumeric value
+    BIGNUMERIC = 13;
+
+    // Interval
+    INTERVAL = 14;
   }
 
   enum Mode {