[FEATURE] Replace get_batch_list_from_batch_request with get_batch an…

…d get_batch_identifiers_list (great-expectations#10295)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Bill Dirks <bill@greatexpectations.io>

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/data_assets/organize_batches_in_pandas_filesystem_datasource.py

@@ -46,23 +46,20 @@
 # Python
 # <snippet name="docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/data_assets/organize_batches_in_pandas_filesystem_datasource.py my_batch_list">
 my_batch_request = my_asset.build_batch_request()
-batches = my_asset.get_batch_list_from_batch_request(my_batch_request)
+batch = my_asset.get_batch(my_batch_request)
 # </snippet>
 
 assert my_batch_request.datasource_name == "my_datasource"
 assert my_batch_request.data_asset_name == "my_taxi_data_asset"
 assert my_batch_request.options == {}
 
-assert len(batches) == 3
 
-for batch in batches:
-    batch_spec = batch.batch_spec
-    assert batch_spec.reader_method == "read_csv"
-    assert batch_spec.reader_options == {}
-    assert batch.data.dataframe.shape == (10000, 18)
+batch_spec = batch.batch_spec
+assert batch_spec.reader_method == "read_csv"
+assert batch_spec.reader_options == {}
+assert batch.data.dataframe.shape == (10000, 18)
 
 # Python
 # <snippet name="docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/data_assets/organize_batches_in_pandas_filesystem_datasource.py print_batch_spec">
-for batch in batches:
-    print(batch.batch_spec)
+print(batch.batch_spec)
 # </snippet>

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/database/how_to_connect_to_postgresql_data.py

@@ -98,9 +98,8 @@
     assert asset
 
     my_batch_request = asset.build_batch_request()
-    batches = asset.get_batch_list_from_batch_request(my_batch_request)
-    assert len(batches) == 1
-    assert set(batches[0].columns()) == {
+    batch = asset.get_batch(my_batch_request)
+    assert set(batch.columns()) == {
         "vendor_id",
         "pickup_datetime",
         "dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/database/how_to_connect_to_sql_data.py

@@ -59,9 +59,8 @@
 assert my_asset
 
 my_batch_request = my_asset.build_batch_request()
-batches = my_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = my_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "vendor_id",
     "pickup_datetime",
     "dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/database/how_to_connect_to_sql_data_using_a_query.py

@@ -56,9 +56,8 @@
 assert my_asset
 
 my_batch_request = my_asset.build_batch_request()
-batches = my_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = my_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "passenger_count",
     "total_amount",
 }

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/filesystem/how_to_connect_to_data_on_azure_blob_storage_using_spark.py

@@ -54,9 +54,8 @@
 assert datasource.get_asset_names() == {"my_taxi_data_asset"}
 
 my_batch_request = data_asset.build_batch_request({"year": "2019", "month": "03"})
-batches = data_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = data_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "vendor_id",
     "pickup_datetime",
     "dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/filesystem/how_to_connect_to_data_on_gcs_using_pandas.py

@@ -45,9 +45,8 @@
 my_batch_request = my_batch_definition.build_batch_request(
     {"year": "2019", "month": "03"}
 )
-batches = data_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = data_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "vendor_id",
     "pickup_datetime",
     "dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/filesystem/how_to_connect_to_data_on_gcs_using_spark.py

@@ -46,9 +46,8 @@
 assert datasource.get_asset_names() == {"my_taxi_data_asset"}
 
 my_batch_request = data_asset.build_batch_request({"year": "2019", "month": "03"})
-batches = data_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = data_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "vendor_id",
     "pickup_datetime",
     "dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/filesystem/how_to_connect_to_data_on_s3_using_spark.py

@@ -46,9 +46,8 @@
 assert datasource.get_asset_names() == {"my_taxi_data_asset"}
 
 my_batch_request = data_asset.build_batch_request({"year": "2019", "month": "03"})
-batches = data_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = data_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "vendor_id",
     "pickup_datetime",
     "dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/filesystem/how_to_connect_to_one_or_more_files_using_pandas.py

@@ -54,9 +54,8 @@
 assert my_asset
 
 my_batch_request = my_asset.build_batch_request({"year": "2019", "month": "03"})
-batches = my_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = my_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "vendor_id",
     "pickup_datetime",
     "dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/filesystem/how_to_connect_to_one_or_more_files_using_spark.py

@@ -59,9 +59,8 @@
 my_batch_request = my_batch_definition.build_batch_request(
     batch_parameters={"year": "2019", "month": "03"}
 )
-batches = my_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = my_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "vendor_id",
     "pickup_datetime",
     "dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/in_memory/how_to_connect_to_in_memory_data_using_pandas.py

@@ -43,9 +43,8 @@
 assert my_batch_request.data_asset_name == "taxi_dataframe"
 assert my_batch_request.options == {}
 
-batches = data_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = data_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "VendorID",
     "tpep_pickup_datetime",
     "tpep_dropoff_datetime",

docs/docusaurus/docs/oss/guides/connecting_to_your_data/fluent/in_memory/how_to_connect_to_in_memory_data_using_spark.py

@@ -63,6 +63,5 @@
 assert my_batch_request.data_asset_name == "my_df_asset"
 assert my_batch_request.options == {}
 
-batches = data_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {"a", "b", "c"}
+batch = data_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {"a", "b", "c"}

docs/docusaurus/docs/snippets/aws_cloud_storage_spark.py

@@ -247,7 +247,7 @@
 
 
 # <snippet name="docs/docusaurus/docs/snippets/aws_cloud_storage_spark.py get_batch_list">
-batches = asset.get_batch_list_from_batch_request(request)
+batch = asset.get_batch(request)
 # </snippet>
 
 config = context.fluent_datasources["s3_datasource"].yaml()

docs/docusaurus/docs/snippets/get_existing_data_asset_from_existing_datasource_pandas_filesystem_example.py

@@ -72,19 +72,15 @@
 
 # Python
 # <snippet name="docs/docusaurus/docs/snippets/get_existing_data_asset_from_existing_datasource_pandas_filesystem_example.py my_batch_list">
-batches = my_asset.get_batch_list_from_batch_request(my_batch_request)
+batch = my_asset.get_batch(my_batch_request)
 # </snippet>
 
-assert len(batches) == 3
-
-for batch in batches:
-    batch_spec = batch.batch_spec
-    assert batch_spec.reader_method == "read_csv"
-    assert batch_spec.reader_options == {}
-    assert batch.data.dataframe.shape == (10000, 18)
+batch_spec = batch.batch_spec
+assert batch_spec.reader_method == "read_csv"
+assert batch_spec.reader_options == {}
+assert batch.data.dataframe.shape == (10000, 18)
 
 # Python
 # <snippet name="docs/docusaurus/docs/snippets/get_existing_data_asset_from_existing_datasource_pandas_filesystem_example.py print_batch_spec">
-for batch in batches:
-    print(batch.batch_spec)
+print(batch.batch_spec)
 # </snippet>

docs/docusaurus/docs/snippets/how_to_connect_to_a_sql_table.py

@@ -54,9 +54,8 @@
 assert my_asset
 
 my_batch_request = my_asset.build_batch_request()
-batches = my_asset.get_batch_list_from_batch_request(my_batch_request)
-assert len(batches) == 1
-assert set(batches[0].columns()) == {
+batch = my_asset.get_batch(my_batch_request)
+assert set(batch.columns()) == {
     "vendor_id",
     "pickup_datetime",
     "dropoff_datetime",
@@ -88,4 +87,4 @@
 )
 # </snippet>
 
-batches = my_asset.get_batch_list_from_batch_request(my_batch_request)
+batch = my_asset.get_batch(my_batch_request)

docs/docusaurus/docs/snippets/organize_batches_in_sqlite_datasource.py

@@ -43,9 +43,8 @@
 # </snippet>
 
 my_batch_request = my_table_asset.build_batch_request(partitioner=partitioner)
-batches = my_table_asset.get_batch_list_from_batch_request(my_batch_request)
+batch = my_table_asset.get_batch(my_batch_request)
 
-assert len(batches) == 12
 
 assert my_table_asset.get_batch_parameters_keys(partitioner=partitioner) == (
     "year",
@@ -55,17 +54,14 @@
 # Python
 # <snippet name="docs/docusaurus/docs/snippets/organize_batches_in_sqlite_datasource.py my_batch_list">
 my_batch_request = my_table_asset.build_batch_request(partitioner=partitioner)
-batches = my_table_asset.get_batch_list_from_batch_request(my_batch_request)
+batch = my_table_asset.get_batch(my_batch_request)
 # </snippet>
 
 assert my_batch_request.datasource_name == "my_datasource"
 assert my_batch_request.data_asset_name == "my_table_asset"
 assert my_batch_request.options == {}
 
-assert len(batches) == 12
-
 # Python
 # <snippet name="docs/docusaurus/docs/snippets/organize_batches_in_sqlite_datasource.py print_batch_spec">
-for batch in batches:
-    print(batch.batch_spec)
+print(batch.batch_spec)
 # </snippet>

docs/sphinx_api_docs_source/public_api_missing_threshold.py

@@ -45,20 +45,14 @@
     "File: great_expectations/datasource/fluent/config.py Name: pop",
     "File: great_expectations/datasource/fluent/config.py Name: yaml",
     "File: great_expectations/datasource/fluent/config_str.py Name: ConfigStr",
-    "File: great_expectations/datasource/fluent/file_path_data_asset.py Name: get_batch_list_from_batch_request",
     "File: great_expectations/datasource/fluent/fluent_base_model.py Name: dict",
     "File: great_expectations/datasource/fluent/fluent_base_model.py Name: yaml",
     "File: great_expectations/datasource/fluent/invalid_datasource.py Name: build_batch_request",
     "File: great_expectations/datasource/fluent/invalid_datasource.py Name: get_asset",
-    "File: great_expectations/datasource/fluent/invalid_datasource.py Name: get_batch_list_from_batch_request",
     "File: great_expectations/datasource/fluent/invalid_datasource.py Name: get_batch_parameters_keys",
     "File: great_expectations/datasource/fluent/pandas_datasource.py Name: dict",
-    "File: great_expectations/datasource/fluent/pandas_datasource.py Name: get_batch_list_from_batch_request",
     "File: great_expectations/datasource/fluent/sources.py Name: add_datasource",
     "File: great_expectations/datasource/fluent/sources.py Name: delete_datasource",
-    "File: great_expectations/datasource/fluent/spark_datasource.py Name: get_batch_list_from_batch_request",
-    "File: great_expectations/datasource/fluent/sql_datasource.py Name: get_batch_list_from_batch_request",
-    "File: great_expectations/datasource/new_datasource.py Name: get_batch_list_from_batch_request",
     "File: great_expectations/exceptions/exceptions.py Name: InvalidExpectationConfigurationError",
     "File: great_expectations/expectations/expectation.py Name: validate_configuration",
     "File: great_expectations/expectations/expectation_configuration.py Name: to_domain_obj",
@@ -68,7 +62,6 @@
     "File: great_expectations/expectations/set_based_column_map_expectation.py Name: register_metric",
     "File: great_expectations/expectations/set_based_column_map_expectation.py Name: validate_configuration",
     "File: great_expectations/experimental/datasource/fabric.py Name: build_batch_request",
-    "File: great_expectations/experimental/datasource/fabric.py Name: get_batch_list_from_batch_request",
     "File: great_expectations/experimental/metric_repository/metric_retriever.py Name: get_validator",
     "File: great_expectations/experimental/rule_based_profiler/helpers/util.py Name: build_batch_request",
     "File: great_expectations/experimental/rule_based_profiler/rule_based_profiler.py Name: run",

great_expectations/core/batch_definition.py

@@ -73,14 +73,8 @@ def get_batch(self, batch_parameters: Optional[BatchParameters] = None) -> Batch
         Returns:
             A Batch of data.
         """
-        batch_list = self.data_asset.get_batch_list_from_batch_request(
-            self.build_batch_request(batch_parameters=batch_parameters)
-        )
-
-        if len(batch_list) == 0:
-            raise ValueError("No batch found")  # noqa: TRY003
-
-        return batch_list[-1]
+        batch_request = self.build_batch_request(batch_parameters=batch_parameters)
+        return self.data_asset.get_batch(batch_request)
 
     def is_added(self) -> BatchDefinitionAddedDiagnostics:
         return BatchDefinitionAddedDiagnostics(