✨ [source-google-sheets] add row_batch_size as an input parameter

airbyte-integrations/connectors/source-google-sheets/metadata.yaml

@@ -10,7 +10,7 @@ data:
   connectorSubtype: file
   connectorType: source
   definitionId: 71607ba1-c0ac-4799-8049-7f4b90dd50f7
-  dockerImageTag: 0.3.16
+  dockerImageTag: 0.3.17
   dockerRepository: airbyte/source-google-sheets
   documentationUrl: https://docs.airbyte.com/integrations/sources/google-sheets
   githubIssueLabel: source-google-sheets

airbyte-integrations/connectors/source-google-sheets/pyproject.toml

@@ -3,7 +3,7 @@ requires = [ "poetry-core>=1.0.0",]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
-version = "0.3.16"
+version = "0.3.17"
 name = "source-google-sheets"
 description = "Source implementation for Google Sheets."
 authors = [ "Airbyte <[email protected]>",]

airbyte-integrations/connectors/source-google-sheets/source_google_sheets/source.py

@@ -148,6 +148,7 @@ def _read(
         state: Union[List[AirbyteStateMessage], MutableMapping[str, Any]] = None,
     ) -> Generator[AirbyteMessage, None, None]:
         client = GoogleSheetsClient(self.get_credentials(config))
+        client.Backoff.row_batch_size = config["batch_size"]
 
         sheet_to_column_name = Helpers.parse_sheet_and_column_names_from_catalog(catalog)
         spreadsheet_id = Helpers.get_spreadsheet_id(config["spreadsheet_id"])

airbyte-integrations/connectors/source-google-sheets/source_google_sheets/spec.yaml

@@ -8,6 +8,13 @@ connectionSpecification:
     - credentials
   additionalProperties: true
   properties:
+    batch_size:
+      type: integer
+      title: Batch Size
+      description: >-
+        An integer representing batch size for each Google Sheets API request.
+        Default value is 200, as it was with previous connector's version.
+      default: 200
     spreadsheet_id:
       type: string
       title: Spreadsheet Link

airbyte-integrations/connectors/source-google-sheets/unit_tests/test_client.py

@@ -65,4 +65,4 @@ def test_client_get_values_on_backoff(caplog):
         majorDimension="ROWS",
     )
 
-    assert "Fetching range sheet!0:220" in caplog.text
+    assert "Fetching range sheet!0:220" in caplog.text

docs/integrations/sources/google-sheets.md

@@ -97,8 +97,9 @@ If your spreadsheet is viewable by anyone with its link, no further action is ne
   - To authenticate your Google account via OAuth, select **Authenticate via Google (OAuth)** from the dropdown and enter your Google application's client ID, client secret, and refresh token.
 <!-- /env:oss -->
 6. For **Spreadsheet Link**, enter the link to the Google spreadsheet. To get the link, go to the Google spreadsheet you want to sync, click **Share** in the top right corner, and click **Copy Link**.
-7. (Optional) You may enable the option to **Convert Column Names to SQL-Compliant Format**. Enabling this option will allow the connector to convert column names to a standardized, SQL-friendly format. For example, a column name of `Café Earnings 2022` will be converted to `cafe_earnings_2022`. We recommend enabling this option if your target destination is SQL-based (ie Postgres, MySQL). Set to false by default.
-8. Click **Set up source** and wait for the tests to complete.
+7. For **Batch Size**, enter an integer which represents batch size when processing a Google Sheet. Default value is 200.
+8. (Optional) You may enable the option to **Convert Column Names to SQL-Compliant Format**. Enabling this option will allow the connector to convert column names to a standardized, SQL-friendly format. For example, a column name of `Café Earnings 2022` will be converted to `cafe_earnings_2022`. We recommend enabling this option if your target destination is SQL-based (ie Postgres, MySQL). Set to false by default.
+9. Click **Set up source** and wait for the tests to complete.
 
 <HideInUI>