.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "3.7.0"
+current_version = "3.7.1"
 commit = false
 tag = false
 tag_name = "{new_version}"

.github/workflows/cfn-nag.yml

@@ -42,11 +42,20 @@ jobs:
           npm install -g aws-cdk
           cdk --version
       - uses: actions/checkout@v4
-      - name: Set up Python ${{ matrix.python-version }}
+      - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: 3.11
       - name: Install Requirements
+        run: |
+          cd test_infra
+          python -m pip install --upgrade pip
+          python -m pip install poetry
+          poetry env use python
+          poetry env info
+          source $(poetry env info --path)/bin/activate
+          poetry install -vvv
+      - name: Set up cdk.json
         run: |
           cd test_infra
           cat <<EOT >> cdk.context.json
@@ -61,12 +70,8 @@ jobs:
             ]
           }
           EOT
-          python -m pip install --upgrade pip
-          python -m pip install poetry
-          poetry env use python
-          poetry env info
-          source $(poetry env info --path)/bin/activate
-          poetry install -vvv
+          cat cdk.json | jq -r '.context.databases.neptune = true' | jq -r '.context.databases.oracle = true' | jq -r '.context.databases.sqlserver = true' > overwrite.cdk.json
+          rm cdk.json && mv overwrite.cdk.json cdk.json
       - name: CDK Synth
         run: |
           cd test_infra

README.md

@@ -100,27 +100,27 @@ 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.
 
-The quickest way to get started is to use AWS Glue with Ray. Read our [docs](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/scale.html), our blogs ([1](https://aws.amazon.com/blogs/big-data/scale-aws-sdk-for-pandas-workloads-with-aws-glue-for-ray/)/[2](https://aws.amazon.com/blogs/big-data/advanced-patterns-with-aws-sdk-for-pandas-on-aws-glue-for-ray/)), or head to our latest [tutorials](https://github.com/aws/aws-sdk-pandas/tree/main/tutorials) to discover even more features.
+The quickest way to get started is to use AWS Glue with Ray. Read our [docs](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/scale.html), our blogs ([1](https://aws.amazon.com/blogs/big-data/scale-aws-sdk-for-pandas-workloads-with-aws-glue-for-ray/)/[2](https://aws.amazon.com/blogs/big-data/advanced-patterns-with-aws-sdk-for-pandas-on-aws-glue-for-ray/)), or head to our latest [tutorials](https://github.com/aws/aws-sdk-pandas/tree/main/tutorials) to discover even more features.
 
 > ⚠️ **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/3.7.0/about.html)
-- [**Install**](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html)
-  - [PyPi (pip)](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#pypi-pip)
-  - [Conda](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#conda)
-  - [AWS Lambda Layer](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#aws-lambda-layer)
-  - [AWS Glue Python Shell Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#aws-glue-python-shell-jobs)
-  - [AWS Glue PySpark Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#aws-glue-pyspark-jobs)
-  - [Amazon SageMaker Notebook](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#amazon-sagemaker-notebook)
-  - [Amazon SageMaker Notebook Lifecycle](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#amazon-sagemaker-notebook-lifecycle)
-  - [EMR](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#emr)
-  - [From source](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/install.html#from-source)
-- [**At scale**](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/scale.html)
-  - [Getting Started](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/scale.html#getting-started)
-  - [Supported APIs](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/scale.html#supported-apis)
-  - [Resources](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/scale.html#resources)
+- [**What is AWS SDK for pandas?**](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/about.html)
+- [**Install**](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html)
+  - [PyPi (pip)](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#pypi-pip)
+  - [Conda](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#conda)
+  - [AWS Lambda Layer](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#aws-lambda-layer)
+  - [AWS Glue Python Shell Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#aws-glue-python-shell-jobs)
+  - [AWS Glue PySpark Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#aws-glue-pyspark-jobs)
+  - [Amazon SageMaker Notebook](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#amazon-sagemaker-notebook)
+  - [Amazon SageMaker Notebook Lifecycle](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#amazon-sagemaker-notebook-lifecycle)
+  - [EMR](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#emr)
+  - [From source](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/install.html#from-source)
+- [**At scale**](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/scale.html)
+  - [Getting Started](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/scale.html#getting-started)
+  - [Supported APIs](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/scale.html#supported-apis)
+  - [Resources](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/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)
@@ -162,30 +162,30 @@ The quickest way to get started is to use AWS Glue with Ray. Read our [docs](htt
   - [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/3.7.0/api.html)
-  - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-s3)
-  - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#aws-glue-catalog)
-  - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-athena)
-  - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-redshift)
-  - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#postgresql)
-  - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#mysql)
-  - [SQL Server](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#sqlserver)
-  - [Oracle](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#oracle)
-  - [Data API Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#data-api-redshift)
-  - [Data API RDS](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#data-api-rds)
-  - [OpenSearch](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#opensearch)
-  - [AWS Glue Data Quality](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#aws-glue-data-quality)
-  - [Amazon Neptune](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-neptune)
-  - [DynamoDB](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#dynamodb)
-  - [Amazon Timestream](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-timestream)
-  - [Amazon EMR](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-emr)
-  - [Amazon CloudWatch Logs](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-cloudwatch-logs)
-  - [Amazon Chime](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-chime)
-  - [Amazon QuickSight](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#amazon-quicksight)
-  - [AWS STS](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#aws-sts)
-  - [AWS Secrets Manager](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#aws-secrets-manager)
-  - [Global Configurations](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#global-configurations)
-  - [Distributed - Ray](https://aws-sdk-pandas.readthedocs.io/en/3.7.0/api.html#distributed-ray)
+- [**API Reference**](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html)
+  - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-s3)
+  - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#aws-glue-catalog)
+  - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-athena)
+  - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-redshift)
+  - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#postgresql)
+  - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#mysql)
+  - [SQL Server](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#sqlserver)
+  - [Oracle](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#oracle)
+  - [Data API Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#data-api-redshift)
+  - [Data API RDS](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#data-api-rds)
+  - [OpenSearch](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#opensearch)
+  - [AWS Glue Data Quality](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#aws-glue-data-quality)
+  - [Amazon Neptune](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-neptune)
+  - [DynamoDB](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#dynamodb)
+  - [Amazon Timestream](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-timestream)
+  - [Amazon EMR](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-emr)
+  - [Amazon CloudWatch Logs](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-cloudwatch-logs)
+  - [Amazon Chime](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-chime)
+  - [Amazon QuickSight](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#amazon-quicksight)
+  - [AWS STS](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#aws-sts)
+  - [AWS Secrets Manager](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#aws-secrets-manager)
+  - [Global Configurations](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/api.html#global-configurations)
+  - [Distributed - Ray](https://aws-sdk-pandas.readthedocs.io/en/3.7.1/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 @@
-3.7.0
+3.7.1

awswrangler/__metadata__.py

@@ -7,5 +7,5 @@
 
 __title__: str = "awswrangler"
 __description__: str = "Pandas on AWS."
-__version__: str = "3.7.0"
+__version__: str = "3.7.1"
 __license__: str = "Apache License 2.0"

awswrangler/athena/_read.py

@@ -792,11 +792,11 @@ def read_sql_query(
 
     **Related tutorial:**
 
-    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.7.0/
+    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.7.1/
       tutorials/006%20-%20Amazon%20Athena.html>`_
-    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.7.0/
+    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.7.1/
       tutorials/019%20-%20Athena%20Cache.html>`_
-    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.7.0/
+    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.7.1/
       tutorials/021%20-%20Global%20Configurations.html>`_
 
     **There are three approaches available through ctas_approach and unload_approach parameters:**
@@ -860,7 +860,7 @@ 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/3.7.0/
+    `related tutorial <https://aws-sdk-pandas.readthedocs.io/en/3.7.1/
     tutorials/024%20-%20Athena%20Query%20Metadata.html>`_!
 
 
@@ -1137,11 +1137,11 @@ def read_sql_table(
 
     **Related tutorial:**
 
-    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.7.0/
+    - `Amazon Athena <https://aws-sdk-pandas.readthedocs.io/en/3.7.1/
       tutorials/006%20-%20Amazon%20Athena.html>`_
-    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.7.0/
+    - `Athena Cache <https://aws-sdk-pandas.readthedocs.io/en/3.7.1/
       tutorials/019%20-%20Athena%20Cache.html>`_
-    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.7.0/
+    - `Global Configurations <https://aws-sdk-pandas.readthedocs.io/en/3.7.1/
       tutorials/021%20-%20Global%20Configurations.html>`_
 
     **There are three approaches available through ctas_approach and unload_approach parameters:**
@@ -1205,7 +1205,7 @@ 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/3.7.0/
+    `related tutorial <https://aws-sdk-pandas.readthedocs.io/en/3.7.1/
     tutorials/024%20-%20Athena%20Query%20Metadata.html>`_!
 
 

awswrangler/catalog/_create.py

@@ -143,12 +143,13 @@ def _create_table(  # noqa: PLR0912,PLR0915
         DatabaseName=database,
         TableInput=table_input,
     )
-    if table_exist and mode in ("overwrite", "update"):
+    if table_exist:
         _logger.debug("Updating table (%s)...", mode)
         args["SkipArchive"] = skip_archive
         if mode == "overwrite":
             delete_all_partitions(table=table, database=database, catalog_id=catalog_id, boto3_session=boto3_session)
-        client_glue.update_table(**args)
+        if mode in ["overwrite", "update"]:
+            client_glue.update_table(**args)
     else:
         try:
             _logger.debug("Creating table (%s)...", mode)
@@ -1079,7 +1080,7 @@ 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/3.7.0/tutorials/014%20-%20Schema%20Evolution.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.7.1/tutorials/014%20-%20Schema%20Evolution.html
     sep : str
         String of length 1. Field delimiter for the output file.
     skip_header_line_count : Optional[int]
@@ -1260,7 +1261,7 @@ 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/3.7.0/tutorials/014%20-%20Schema%20Evolution.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.7.1/tutorials/014%20-%20Schema%20Evolution.html
     serde_library : Optional[str]
         Specifies the SerDe Serialization library which will be used. You need to provide the Class library name
         as a string.

awswrangler/redshift/_write.py

@@ -122,7 +122,7 @@ def to_sql(
         Dictionary of columns names and Redshift types to be casted.
         Useful when you have columns with undetermined or mixed data types.
         (e.g. {'col name': 'VARCHAR(10)', 'col2 name': 'FLOAT'})
-        diststyle : str
+    diststyle : str
         Redshift distribution styles. Must be in ["AUTO", "EVEN", "ALL", "KEY"].
         https://docs.aws.amazon.com/redshift/latest/dg/t_Distributing_data.html
     distkey : str, optional

awswrangler/s3/_read_orc.py

@@ -224,7 +224,7 @@ 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/3.7.0/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.7.1/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
     columns : List[str], optional
         List of columns to read from the file(s).
     validate_schema : bool, default False
@@ -386,7 +386,7 @@ 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/3.7.0/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.7.1/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
     columns : List[str], optional
         List of columns to read from the file(s).
     validate_schema : bool, default False

awswrangler/s3/_read_parquet.py

@@ -397,7 +397,7 @@ def read_parquet(
         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/3.7.0/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.7.1/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
     columns : List[str], optional
         List of columns to read from the file(s).
     validate_schema : bool, default False
@@ -639,7 +639,7 @@ def read_parquet_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/3.7.0/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
+        https://aws-sdk-pandas.readthedocs.io/en/3.7.1/tutorials/023%20-%20Flexible%20Partitions%20Filter.html
     columns : List[str], optional
         List of columns to read from the file(s).
     validate_schema : bool, default False