Merge branch 'main' into chore/publish-workflow

Author: kukushking

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "3.13.0"
+current_version = "3.14.0"
 commit = false
 tag = false
 tag_name = "{new_version}"

.github/workflows/snyk.yml

@@ -16,7 +16,7 @@ jobs:
     steps:
       - uses: actions/checkout@v5
       - name: Run Snyk to check for vulnerabilities
-        uses: snyk/actions/python-3.8@master
+        uses: snyk/actions/python-3.12@master
         continue-on-error: true  # To make sure that SARIF upload gets called
         env:
           SNYK_TOKEN: ${{ secrets.SNYK_TOKEN }}

README.md

@@ -94,25 +94,25 @@ 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/3.13.0/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/3.14.0/scale.html) or head to our latest [tutorials](https://github.com/aws/aws-sdk-pandas/tree/main/tutorials) to learn more.
 
 ## [Read The Docs](https://aws-sdk-pandas.readthedocs.io/)
 
-- [**What is AWS SDK for pandas?**](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/about.html)
-- [**Install**](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html)
-  - [PyPi (pip)](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#pypi-pip)
-  - [Conda](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#conda)
-  - [AWS Lambda Layer](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#aws-lambda-layer)
-  - [AWS Glue Python Shell Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#aws-glue-python-shell-jobs)
-  - [AWS Glue PySpark Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#aws-glue-pyspark-jobs)
-  - [Amazon SageMaker Notebook](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#amazon-sagemaker-notebook)
-  - [Amazon SageMaker Notebook Lifecycle](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#amazon-sagemaker-notebook-lifecycle)
-  - [EMR](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#emr)
-  - [From source](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/install.html#from-source)
-- [**At scale**](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/scale.html)
-  - [Getting Started](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/scale.html#getting-started)
-  - [Supported APIs](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/scale.html#supported-apis)
-  - [Resources](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/scale.html#resources)
+- [**What is AWS SDK for pandas?**](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/about.html)
+- [**Install**](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html)
+  - [PyPi (pip)](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#pypi-pip)
+  - [Conda](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#conda)
+  - [AWS Lambda Layer](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#aws-lambda-layer)
+  - [AWS Glue Python Shell Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#aws-glue-python-shell-jobs)
+  - [AWS Glue PySpark Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#aws-glue-pyspark-jobs)
+  - [Amazon SageMaker Notebook](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#amazon-sagemaker-notebook)
+  - [Amazon SageMaker Notebook Lifecycle](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#amazon-sagemaker-notebook-lifecycle)
+  - [EMR](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#emr)
+  - [From source](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/install.html#from-source)
+- [**At scale**](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/scale.html)
+  - [Getting Started](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/scale.html#getting-started)
+  - [Supported APIs](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/scale.html#supported-apis)
+  - [Resources](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/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)
@@ -153,30 +153,30 @@ Read our [docs](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/scale.html) or h
   - [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/3.13.0/api.html)
-  - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-s3)
-  - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#aws-glue-catalog)
-  - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-athena)
-  - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-redshift)
-  - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#postgresql)
-  - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#mysql)
-  - [SQL Server](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#sqlserver)
-  - [Oracle](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#oracle)
-  - [Data API Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#data-api-redshift)
-  - [Data API RDS](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#data-api-rds)
-  - [OpenSearch](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#opensearch)
-  - [AWS Glue Data Quality](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#aws-glue-data-quality)
-  - [Amazon Neptune](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-neptune)
-  - [DynamoDB](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#dynamodb)
-  - [Amazon Timestream](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-timestream)
-  - [Amazon EMR](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-emr)
-  - [Amazon CloudWatch Logs](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-cloudwatch-logs)
-  - [Amazon Chime](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-chime)
-  - [Amazon QuickSight](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#amazon-quicksight)
-  - [AWS STS](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#aws-sts)
-  - [AWS Secrets Manager](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#aws-secrets-manager)
-  - [Global Configurations](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#global-configurations)
-  - [Distributed - Ray](https://aws-sdk-pandas.readthedocs.io/en/3.13.0/api.html#distributed-ray)
+- [**API Reference**](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html)
+  - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-s3)
+  - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#aws-glue-catalog)
+  - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-athena)
+  - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-redshift)
+  - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#postgresql)
+  - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#mysql)
+  - [SQL Server](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#sqlserver)
+  - [Oracle](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#oracle)
+  - [Data API Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#data-api-redshift)
+  - [Data API RDS](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#data-api-rds)
+  - [OpenSearch](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#opensearch)
+  - [AWS Glue Data Quality](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#aws-glue-data-quality)
+  - [Amazon Neptune](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-neptune)
+  - [DynamoDB](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#dynamodb)
+  - [Amazon Timestream](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-timestream)
+  - [Amazon EMR](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-emr)
+  - [Amazon CloudWatch Logs](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-cloudwatch-logs)
+  - [Amazon Chime](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-chime)
+  - [Amazon QuickSight](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#amazon-quicksight)
+  - [AWS STS](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#aws-sts)
+  - [AWS Secrets Manager](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#aws-secrets-manager)
+  - [Global Configurations](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/api.html#global-configurations)
+  - [Distributed - Ray](https://aws-sdk-pandas.readthedocs.io/en/3.14.0/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 @@
-3.13.0
+3.14.0

awswrangler/__metadata__.py

@@ -7,5 +7,5 @@
 
 __title__: str = "awswrangler"
 __description__: str = "Pandas on AWS."
-__version__: str = "3.13.0"
+__version__: str = "3.14.0"
 __license__: str = "Apache License 2.0"

awswrangler/_distributed.py

@@ -177,7 +177,7 @@ def get(cls) -> MemoryFormatEnum:
             return cls._enum if cls._enum else cls.get_installed()
 
     @classmethod
-    def set(cls, name: EngineLiteral) -> None:
+    def set(cls, name: MemoryFormatLiteral) -> None:
         """Set the memory format."""
         with cls._lock:
             cls._enum = MemoryFormatEnum[name.upper()]

awswrangler/athena/_read.py

@@ -798,11 +798,11 @@ def read_sql_query(
 
     **Related tutorial:**
 
-    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.13.0/
+    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.14.0/
       tutorials/006%20-%20Amazon%20Athena.html>`_
-    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.13.0/
+    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.14.0/
       tutorials/019%20-%20Athena%20Cache.html>`_
-    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.13.0/
+    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.14.0/
       tutorials/021%20-%20Global%20Configurations.html>`_
 
     **There are three approaches available through ctas_approach and unload_approach parameters:**
@@ -866,7 +866,7 @@ 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/3.13.0/
+    `related tutorial <https://aws-sdk-pandas.readthedocs.io/en/3.14.0/
     tutorials/024%20-%20Athena%20Query%20Metadata.html>`_!
 
 
@@ -1154,11 +1154,11 @@ def read_sql_table(
 
     **Related tutorial:**
 
-    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.13.0/
+    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.14.0/
       tutorials/006%20-%20Amazon%20Athena.html>`_
-    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.13.0/
+    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.14.0/
       tutorials/019%20-%20Athena%20Cache.html>`_
-    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.13.0/
+    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.14.0/
       tutorials/021%20-%20Global%20Configurations.html>`_
 
     **There are three approaches available through ctas_approach and unload_approach parameters:**
@@ -1222,7 +1222,7 @@ 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/3.13.0/
+    `related tutorial <https://aws-sdk-pandas.readthedocs.io/en/3.14.0/
     tutorials/024%20-%20Athena%20Query%20Metadata.html>`_!
 
 

awswrangler/athena/_write_iceberg.py

@@ -578,6 +578,7 @@ def to_iceberg(  # noqa: PLR0913
                 keep_files=False,
                 data_source=data_source,
                 workgroup=workgroup,
+                s3_output=s3_output,
                 encryption=encryption,
                 kms_key=kms_key,
                 boto3_session=boto3_session,
@@ -593,6 +594,7 @@ def to_iceberg(  # noqa: PLR0913
                 wg_config=wg_config,
                 database=database,
                 data_source=data_source,
+                s3_output=s3_output,
                 encryption=encryption,
                 kms_key=kms_key,
                 boto3_session=boto3_session,

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/3.13.0/tutorials/014%20-%20Schema%20Evolution.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.14.0/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/3.13.0/tutorials/014%20-%20Schema%20Evolution.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.14.0/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/oracle.py

@@ -607,7 +607,7 @@ def detect_oracle_decimal_datatype(cursor: Any) -> dict[str, pa.DataType]:
     if isinstance(cursor, oracledb.Cursor):
         # Oracle stores DECIMAL as the NUMBER type
 
-        for name, db_type, display_size, internal_size, precision, scale, null_ok in cursor.description:
+        for name, db_type, display_size, internal_size, precision, scale, null_ok in cursor.description:  # type: ignore
             _logger.debug((name, db_type, display_size, internal_size, precision, scale, null_ok))
 
             if db_type == oracledb.DB_TYPE_NUMBER and scale is not None and scale > 0: