Merge branch 'main' into 2956-athena-read_sql_query-provides-completely-wrong-results-for-qmark-style-parametrized-queries-with-cache-enabled

Author: LeonLuttenberger

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "3.9.2b1"
+current_version = "3.10.0"
 commit = false
 tag = false
 tag_name = "{new_version}"

README.md

@@ -94,27 +94,27 @@ FROM "sampleDB"."sampleTable" ORDER BY time DESC LIMIT 3
 ## At scale
 AWS SDK for pandas can also run your workflows at scale by leveraging [Modin](https://modin.readthedocs.io/en/stable/) and [Ray](https://www.ray.io/). Both projects aim to speed up data workloads by distributing processing over a cluster of workers.
 
-Read our [docs](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/scale.html) or head to our latest [tutorials](https://github.com/aws/aws-sdk-pandas/tree/main/tutorials) to learn more.
+Read our [docs](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/scale.html) or head to our latest [tutorials](https://github.com/aws/aws-sdk-pandas/tree/main/tutorials) to learn more.
 
 > ⚠️ **Ray is currently not available for Python 3.12. While AWS SDK for pandas supports Python 3.12, it cannot be used at scale.**
 
 ## [Read The Docs](https://aws-sdk-pandas.readthedocs.io/)
 
-- [**What is AWS SDK for pandas?**](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/about.html)
-- [**Install**](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html)
-  - [PyPi (pip)](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#pypi-pip)
-  - [Conda](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#conda)
-  - [AWS Lambda Layer](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#aws-lambda-layer)
-  - [AWS Glue Python Shell Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#aws-glue-python-shell-jobs)
-  - [AWS Glue PySpark Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#aws-glue-pyspark-jobs)
-  - [Amazon SageMaker Notebook](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#amazon-sagemaker-notebook)
-  - [Amazon SageMaker Notebook Lifecycle](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#amazon-sagemaker-notebook-lifecycle)
-  - [EMR](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#emr)
-  - [From source](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/install.html#from-source)
-- [**At scale**](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/scale.html)
-  - [Getting Started](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/scale.html#getting-started)
-  - [Supported APIs](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/scale.html#supported-apis)
-  - [Resources](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/scale.html#resources)
+- [**What is AWS SDK for pandas?**](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/about.html)
+- [**Install**](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html)
+  - [PyPi (pip)](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#pypi-pip)
+  - [Conda](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#conda)
+  - [AWS Lambda Layer](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#aws-lambda-layer)
+  - [AWS Glue Python Shell Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#aws-glue-python-shell-jobs)
+  - [AWS Glue PySpark Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#aws-glue-pyspark-jobs)
+  - [Amazon SageMaker Notebook](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#amazon-sagemaker-notebook)
+  - [Amazon SageMaker Notebook Lifecycle](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#amazon-sagemaker-notebook-lifecycle)
+  - [EMR](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#emr)
+  - [From source](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/install.html#from-source)
+- [**At scale**](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/scale.html)
+  - [Getting Started](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/scale.html#getting-started)
+  - [Supported APIs](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/scale.html#supported-apis)
+  - [Resources](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/scale.html#resources)
 - [**Tutorials**](https://github.com/aws/aws-sdk-pandas/tree/main/tutorials)
   - [001 - Introduction](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/001%20-%20Introduction.ipynb)
   - [002 - Sessions](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/002%20-%20Sessions.ipynb)
@@ -155,30 +155,30 @@ Read our [docs](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/scale.html) or
   - [039 - Athena Iceberg](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/039%20-%20Athena%20Iceberg.ipynb)
   - [040 - EMR Serverless](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/040%20-%20EMR%20Serverless.ipynb)
   - [041 - Apache Spark on Amazon Athena](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/041%20-%20Apache%20Spark%20on%20Amazon%20Athena.ipynb)
-- [**API Reference**](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html)
-  - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-s3)
-  - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#aws-glue-catalog)
-  - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-athena)
-  - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-redshift)
-  - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#postgresql)
-  - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#mysql)
-  - [SQL Server](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#sqlserver)
-  - [Oracle](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#oracle)
-  - [Data API Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#data-api-redshift)
-  - [Data API RDS](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#data-api-rds)
-  - [OpenSearch](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#opensearch)
-  - [AWS Glue Data Quality](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#aws-glue-data-quality)
-  - [Amazon Neptune](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-neptune)
-  - [DynamoDB](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#dynamodb)
-  - [Amazon Timestream](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-timestream)
-  - [Amazon EMR](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-emr)
-  - [Amazon CloudWatch Logs](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-cloudwatch-logs)
-  - [Amazon Chime](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-chime)
-  - [Amazon QuickSight](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#amazon-quicksight)
-  - [AWS STS](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#aws-sts)
-  - [AWS Secrets Manager](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#aws-secrets-manager)
-  - [Global Configurations](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#global-configurations)
-  - [Distributed - Ray](https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/api.html#distributed-ray)
+- [**API Reference**](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html)
+  - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-s3)
+  - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#aws-glue-catalog)
+  - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-athena)
+  - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-redshift)
+  - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#postgresql)
+  - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#mysql)
+  - [SQL Server](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#sqlserver)
+  - [Oracle](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#oracle)
+  - [Data API Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#data-api-redshift)
+  - [Data API RDS](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#data-api-rds)
+  - [OpenSearch](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#opensearch)
+  - [AWS Glue Data Quality](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#aws-glue-data-quality)
+  - [Amazon Neptune](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-neptune)
+  - [DynamoDB](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#dynamodb)
+  - [Amazon Timestream](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-timestream)
+  - [Amazon EMR](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-emr)
+  - [Amazon CloudWatch Logs](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-cloudwatch-logs)
+  - [Amazon Chime](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-chime)
+  - [Amazon QuickSight](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#amazon-quicksight)
+  - [AWS STS](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#aws-sts)
+  - [AWS Secrets Manager](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#aws-secrets-manager)
+  - [Global Configurations](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#global-configurations)
+  - [Distributed - Ray](https://aws-sdk-pandas.readthedocs.io/en/3.10.0/api.html#distributed-ray)
 - [**License**](https://github.com/aws/aws-sdk-pandas/blob/main/LICENSE.txt)
 - [**Contributing**](https://github.com/aws/aws-sdk-pandas/blob/main/CONTRIBUTING.md)
 

VERSION

@@ -1 +1 @@
-3.9.2b1
+3.10.0

awswrangler/__metadata__.py

@@ -7,5 +7,5 @@
 
 __title__: str = "awswrangler"
 __description__: str = "Pandas on AWS."
-__version__: str = "3.9.2b1"
+__version__: str = "3.10.0"
 __license__: str = "Apache License 2.0"

awswrangler/_config.py

@@ -224,6 +224,9 @@ def _apply_type(name: str, value: Any, dtype: type[_ConfigValueType], nullable:
             raise exceptions.InvalidArgumentValue(
                 f"{name} configuration does not accept a null value. Please pass {dtype}."
             )
+        # Handle case where string is empty, "False" or "0". Anything else is True
+        if isinstance(value, str) and dtype is bool:
+            return value.lower() not in ("false", "0", "")
         try:
             return dtype(value) if isinstance(value, dtype) is False else value
         except ValueError as ex:

awswrangler/_data_types.py

@@ -213,6 +213,8 @@ def pyarrow2postgresql(  # noqa: PLR0911
         return pyarrow2postgresql(dtype=dtype.value_type, string_type=string_type)
     if pa.types.is_binary(dtype):
         return "BYTEA"
+    if pa.types.is_list(dtype):
+        return pyarrow2postgresql(dtype=dtype.value_type, string_type=string_type) + "[]"
     raise exceptions.UnsupportedType(f"Unsupported PostgreSQL type: {dtype}")
 
 

awswrangler/_databases.py

@@ -359,6 +359,8 @@ def generate_placeholder_parameter_pairs(
     """Extract Placeholder and Parameter pairs."""
 
     def convert_value_to_native_python_type(value: Any) -> Any:
+        if isinstance(value, list):
+            return value
         if pd.isna(value):
             return None
         if hasattr(value, "to_pydatetime"):

awswrangler/athena/_read.py

@@ -793,11 +793,11 @@ def read_sql_query(
 
     **Related tutorial:**
 
-    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/
+    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.10.0/
       tutorials/006%20-%20Amazon%20Athena.html>`_
-    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/
+    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.10.0/
       tutorials/019%20-%20Athena%20Cache.html>`_
-    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/
+    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.10.0/
       tutorials/021%20-%20Global%20Configurations.html>`_
 
     **There are three approaches available through ctas_approach and unload_approach parameters:**
@@ -861,7 +861,7 @@ def read_sql_query(
     /athena.html#Athena.Client.get_query_execution>`_ .
 
     For a practical example check out the
-    `related tutorial <https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/
+    `related tutorial <https://aws-sdk-pandas.readthedocs.io/en/3.10.0/
     tutorials/024%20-%20Athena%20Query%20Metadata.html>`_!
 
 
@@ -1138,11 +1138,11 @@ def read_sql_table(
 
     **Related tutorial:**
 
-    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/
+    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.10.0/
       tutorials/006%20-%20Amazon%20Athena.html>`_
-    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/
+    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.10.0/
       tutorials/019%20-%20Athena%20Cache.html>`_
-    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/
+    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.10.0/
       tutorials/021%20-%20Global%20Configurations.html>`_
 
     **There are three approaches available through ctas_approach and unload_approach parameters:**
@@ -1206,7 +1206,7 @@ def read_sql_table(
     /athena.html#Athena.Client.get_query_execution>`_ .
 
     For a practical example check out the
-    `related tutorial <https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/
+    `related tutorial <https://aws-sdk-pandas.readthedocs.io/en/3.10.0/
     tutorials/024%20-%20Athena%20Query%20Metadata.html>`_!
 
 

awswrangler/athena/_write_iceberg.py

@@ -115,7 +115,13 @@ def _determine_differences(
 
     catalog_column_types = typing.cast(
         Dict[str, str],
-        catalog.get_table_types(database=database, table=table, catalog_id=catalog_id, boto3_session=boto3_session),
+        catalog.get_table_types(
+            database=database,
+            table=table,
+            catalog_id=catalog_id,
+            filter_iceberg_current=True,
+            boto3_session=boto3_session,
+        ),
     )
 
     original_column_names = set(catalog_column_types)

awswrangler/catalog/_create.py

@@ -1100,7 +1100,7 @@ def create_csv_table(
         If True allows schema evolution (new or missing columns), otherwise a exception will be raised.
         (Only considered if dataset=True and mode in ("append", "overwrite_partitions"))
         Related tutorial:
-        https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/tutorials/014%20-%20Schema%20Evolution.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.10.0/tutorials/014%20-%20Schema%20Evolution.html
     sep
         String of length 1. Field delimiter for the output file.
     skip_header_line_count
@@ -1280,7 +1280,7 @@ def create_json_table(
         If True allows schema evolution (new or missing columns), otherwise a exception will be raised.
         (Only considered if dataset=True and mode in ("append", "overwrite_partitions"))
         Related tutorial:
-        https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/tutorials/014%20-%20Schema%20Evolution.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.10.0/tutorials/014%20-%20Schema%20Evolution.html
     serde_library
         Specifies the SerDe Serialization library which will be used. You need to provide the Class library name
         as a string.

awswrangler/catalog/_get.py

@@ -107,6 +107,7 @@ def get_table_types(
     database: str,
     table: str,
     catalog_id: str | None = None,
+    filter_iceberg_current: bool = False,
     boto3_session: boto3.Session | None = None,
 ) -> dict[str, str] | None:
     """Get all columns and types from a table.
@@ -120,6 +121,9 @@ def get_table_types(
     catalog_id
         The ID of the Data Catalog from which to retrieve Databases.
         If ``None`` is provided, the AWS account ID is used by default.
+    filter_iceberg_current
+        If True, returns only current iceberg fields (fields marked with iceberg.field.current: true).
+        Otherwise, returns the all fields. False by default (return all fields).
     boto3_session
         The default boto3 session will be used if **boto3_session** receive ``None``.
 
@@ -139,7 +143,10 @@ def get_table_types(
         response = client_glue.get_table(**_catalog_id(catalog_id=catalog_id, DatabaseName=database, Name=table))
     except client_glue.exceptions.EntityNotFoundException:
         return None
-    return _extract_dtypes_from_table_details(response=response)
+    return _extract_dtypes_from_table_details(
+        response=response,
+        filter_iceberg_current=filter_iceberg_current,
+    )
 
 
 def get_databases(

awswrangler/catalog/_utils.py

@@ -31,10 +31,16 @@ def _sanitize_name(name: str) -> str:
     return re.sub("[^A-Za-z0-9_]+", "_", name).lower()  # Replacing non alphanumeric characters by underscore
 
 
-def _extract_dtypes_from_table_details(response: "GetTableResponseTypeDef") -> dict[str, str]:
+def _extract_dtypes_from_table_details(
+    response: "GetTableResponseTypeDef",
+    filter_iceberg_current: bool = False,
+) -> dict[str, str]:
     dtypes: dict[str, str] = {}
     for col in response["Table"]["StorageDescriptor"]["Columns"]:
-        dtypes[col["Name"]] = col["Type"]
+        # Only return current fields if flag is enabled
+        if not filter_iceberg_current or col.get("Parameters", {}).get("iceberg.field.current") == "true":
+            dtypes[col["Name"]] = col["Type"]
+    # Add partition keys as columns
     if "PartitionKeys" in response["Table"]:
         for par in response["Table"]["PartitionKeys"]:
             dtypes[par["Name"]] = par["Type"]

awswrangler/data_api/rds.py

@@ -359,6 +359,9 @@ def _create_value_dict(  # noqa: PLR0911
     if isinstance(value, Decimal):
         return {"stringValue": str(value)}, "DECIMAL"
 
+    if isinstance(value, uuid.UUID):
+        return {"stringValue": str(value)}, "UUID"
+
     raise exceptions.InvalidArgumentType(f"Value {value} not supported.")
 
 

awswrangler/opensearch/_write.py

@@ -504,6 +504,7 @@ def index_documents(
     initial_backoff: int | None = None,
     max_backoff: int | None = None,
     use_threads: bool | int = False,
+    enable_refresh_interval: bool = True,
     **kwargs: Any,
 ) -> dict[str, Any]:
     """
@@ -559,6 +560,8 @@ def index_documents(
         True to enable concurrent requests, False to disable multiple threads.
         If enabled os.cpu_count() will be used as the max number of threads.
         If integer is provided, specified number is used.
+    enable_refresh_interval
+        True (default) to enable ``refresh_interval`` modification to ``-1`` (disabled) while indexing documents
     **kwargs
         KEYWORD arguments forwarded to bulk operation
         elasticsearch >= 7.10.2 / opensearch: \
@@ -614,7 +617,7 @@ def index_documents(
                 widgets=widgets, max_value=total_documents, prefix="Indexing: "
             ).start()
         for i, bulk_chunk_documents in enumerate(actions):
-            if i == 1:  # second bulk iteration, in case the index didn't exist before
+            if i == 1 and enable_refresh_interval:  # second bulk iteration, in case the index didn't exist before
                 refresh_interval = _get_refresh_interval(client, index)
                 _disable_refresh_interval(client, index)
             _logger.debug("running bulk index of %s documents", len(bulk_chunk_documents))
@@ -655,6 +658,7 @@ def index_documents(
             raise e
 
     finally:
-        _set_refresh_interval(client, index, refresh_interval)
+        if enable_refresh_interval:
+            _set_refresh_interval(client, index, refresh_interval)
 
     return {"success": success, "errors": errors}

awswrangler/s3/_read_orc.py

@@ -225,7 +225,7 @@ def read_orc(
         must return a bool, True to read the partition or False to ignore it.
         Ignored if `dataset=False`.
         E.g ``lambda x: True if x["year"] == "2020" and x["month"] == "1" else False``
-        https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.10.0/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
     columns
         List of columns to read from the file(s).
     validate_schema
@@ -384,7 +384,7 @@ def read_orc_table(
         must return a bool, True to read the partition or False to ignore it.
         Ignored if `dataset=False`.
         E.g ``lambda x: True if x["year"] == "2020" and x["month"] == "1" else False``
-        https://aws-sdk-pandas.readthedocs.io/en/3.9.2b1/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.10.0/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
     columns
         List of columns to read from the file(s).
     validate_schema