feat: add estimated physical file sizes to ReadAPI v1 (#605)

* feat: add estimated physical file sizes to ReadAPI v1

PiperOrigin-RevId: 542350532

Source-Link: googleapis/googleapis@a4ff1c2

Source-Link: googleapis/googleapis-gen@b5b5fe5
Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiYjViNWZlNWRjZDRiY2UxNWI3YjkwMzViOTI1NDUyZWU3Y2FmNDg5YiJ9

* 🦉 Updates from OwlBot post-processor

See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md

---------

Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>
Co-authored-by: Anthonios Partheniou <[email protected]>

Author: gcf-owl-bot[bot]

packages/google-cloud-bigquery-storage/google/cloud/bigquery_storage_v1/types/stream.py

@@ -134,6 +134,15 @@ class ReadSession(proto.Message):
             are completely consumed. This estimate is based
             on metadata from the table which might be
             incomplete or stale.
+        estimated_total_physical_file_size (int):
+            Output only. A pre-projected estimate of the
+            total physical size (in bytes) of files this
+            session will scan when all streams are
+            completely consumed. This estimate does not
+            depend on the selected columns and can be based
+            on metadata from the table which might be
+            incomplete or stale. Only set for BigLake
+            tables.
         estimated_row_count (int):
             Output only. An estimate on the number of
             rows present in this session's streams. This
@@ -233,11 +242,11 @@ class TableReadOptions(proto.Message):
             sample_percentage (float):
                 Optional. Specifies a table sampling percentage.
                 Specifically, the query planner will use TABLESAMPLE SYSTEM
-                (sample_percentage PERCENT). This samples at the file-level.
-                It will randomly choose for each file whether to include
-                that file in the sample returned. Note, that if the table
-                only has one file, then TABLESAMPLE SYSTEM will select that
-                file and return all returnable rows contained within.
+                (sample_percentage PERCENT). The sampling percentage is
+                applied at the data block granularity. It will randomly
+                choose for each data block whether to read the rows in that
+                data block. For more details, see
+                https://cloud.google.com/bigquery/docs/table-sampling)
 
                 This field is a member of `oneof`_ ``_sample_percentage``.
         """
@@ -317,6 +326,10 @@ class TableReadOptions(proto.Message):
         proto.INT64,
         number=12,
     )
+    estimated_total_physical_file_size: int = proto.Field(
+        proto.INT64,
+        number=15,
+    )
     estimated_row_count: int = proto.Field(
         proto.INT64,
         number=14,

packages/google-cloud-bigquery-storage/samples/generated_samples/snippet_metadata_google.cloud.bigquery.storage.v1.json

@@ -8,7 +8,7 @@
     ],
     "language": "PYTHON",
     "name": "google-cloud-bigquery-storage",
-    "version": "2.20.0"
+    "version": "0.1.0"
   },
   "snippets": [
     {

packages/google-cloud-bigquery-storage/samples/generated_samples/snippet_metadata_google.cloud.bigquery.storage.v1beta2.json

@@ -8,7 +8,7 @@
     ],
     "language": "PYTHON",
     "name": "google-cloud-bigquery-storage",
-    "version": "2.20.0"
+    "version": "0.1.0"
   },
   "snippets": [
     {

packages/google-cloud-bigquery-storage/tests/unit/gapic/bigquery_storage_v1/test_big_query_read.py

@@ -702,6 +702,7 @@ def test_create_read_session(request_type, transport: str = "grpc"):
             data_format=stream.DataFormat.AVRO,
             table="table_value",
             estimated_total_bytes_scanned=3076,
+            estimated_total_physical_file_size=3608,
             estimated_row_count=2047,
             trace_id="trace_id_value",
             avro_schema=avro.AvroSchema(schema="schema_value"),
@@ -719,6 +720,7 @@ def test_create_read_session(request_type, transport: str = "grpc"):
     assert response.data_format == stream.DataFormat.AVRO
     assert response.table == "table_value"
     assert response.estimated_total_bytes_scanned == 3076
+    assert response.estimated_total_physical_file_size == 3608
     assert response.estimated_row_count == 2047
     assert response.trace_id == "trace_id_value"
 
@@ -765,6 +767,7 @@ async def test_create_read_session_async(
                 data_format=stream.DataFormat.AVRO,
                 table="table_value",
                 estimated_total_bytes_scanned=3076,
+                estimated_total_physical_file_size=3608,
                 estimated_row_count=2047,
                 trace_id="trace_id_value",
             )
@@ -782,6 +785,7 @@ async def test_create_read_session_async(
     assert response.data_format == stream.DataFormat.AVRO
     assert response.table == "table_value"
     assert response.estimated_total_bytes_scanned == 3076
+    assert response.estimated_total_physical_file_size == 3608
     assert response.estimated_row_count == 2047
     assert response.trace_id == "trace_id_value"