.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "3.7.2"
+current_version = "3.7.3"
 commit = false
 tag = false
 tag_name = "{new_version}"

README.md

@@ -1,12 +1,10 @@
 # AWS SDK for pandas (awswrangler)
 
-AWS Data Wrangler is now **AWS SDK for pandas (awswrangler)**.  We’re changing the name we use when we talk about the library, but everything else will stay the same.  You’ll still be able to install using `pip install awswrangler` and you won’t need to change any of your code.  As part of this change, we’ve moved the library from AWS Labs to the main AWS GitHub organisation but, thanks to the GitHub’s redirect feature, you’ll still be able to access the project by its old URLs until you update your bookmarks.  Our documentation has also moved to [aws-sdk-pandas.readthedocs.io](https://aws-sdk-pandas.readthedocs.io), but old bookmarks will redirect to the new site.
-
 *Pandas on AWS*
 
 Easy integration with Athena, Glue, Redshift, Timestream, OpenSearch, Neptune, QuickSight, Chime, CloudWatchLogs, DynamoDB, EMR, SecretManager, PostgreSQL, MySQL, SQLServer and S3 (Parquet, CSV, JSON and EXCEL).
 
-![AWS SDK for pandas](docs/source/_static/logo2.png?raw=true "AWS SDK for pandas")
+![AWS SDK for pandas](https://github.com/aws/aws-sdk-pandas/blob/main/docs/source/_static/logo2.png?raw=true "AWS SDK for pandas")
 ![tracker](https://d3tiqpr4kkkomd.cloudfront.net/img/pixel.png?asset=GVOYN2BOOQ573LTVIHEW)
 
 > An [AWS Professional Service](https://aws.amazon.com/professional-services/) open source initiative | aws-proserve-opensource@amazon.com
@@ -29,17 +27,13 @@ Easy integration with Athena, Glue, Redshift, Timestream, OpenSearch, Neptune, Q
 > ⚠️ **Starting version 3.0, optional modules must be installed explicitly:**<br>
 ➡️`pip install 'awswrangler[redshift]'`
 
-Powered By [<img src="https://arrow.apache.org/img/arrow.png" width="200">](https://arrow.apache.org/powered_by/)
-
 ## Table of contents
 
 - [Quick Start](#quick-start)
 - [At Scale](#at-scale)
 - [Read The Docs](#read-the-docs)
 - [Getting Help](#getting-help)
-- [Community Resources](#community-resources)
 - [Logging](#logging)
-- [Who uses AWS SDK for pandas?](#who-uses-aws-sdk-for-pandas)
 
 ## Quick Start
 
@@ -100,27 +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.
 
-The quickest way to get started is to use AWS Glue with Ray. Read our [docs](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/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.
+Read our [docs](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/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/3.7.2/about.html)
-- [**Install**](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html)
-  - [PyPi (pip)](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#pypi-pip)
-  - [Conda](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#conda)
-  - [AWS Lambda Layer](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#aws-lambda-layer)
-  - [AWS Glue Python Shell Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#aws-glue-python-shell-jobs)
-  - [AWS Glue PySpark Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#aws-glue-pyspark-jobs)
-  - [Amazon SageMaker Notebook](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#amazon-sagemaker-notebook)
-  - [Amazon SageMaker Notebook Lifecycle](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#amazon-sagemaker-notebook-lifecycle)
-  - [EMR](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#emr)
-  - [From source](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/install.html#from-source)
-- [**At scale**](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/scale.html)
-  - [Getting Started](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/scale.html#getting-started)
-  - [Supported APIs](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/scale.html#supported-apis)
-  - [Resources](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/scale.html#resources)
+- [**What is AWS SDK for pandas?**](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/about.html)
+- [**Install**](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html)
+  - [PyPi (pip)](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#pypi-pip)
+  - [Conda](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#conda)
+  - [AWS Lambda Layer](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#aws-lambda-layer)
+  - [AWS Glue Python Shell Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#aws-glue-python-shell-jobs)
+  - [AWS Glue PySpark Jobs](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#aws-glue-pyspark-jobs)
+  - [Amazon SageMaker Notebook](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#amazon-sagemaker-notebook)
+  - [Amazon SageMaker Notebook Lifecycle](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#amazon-sagemaker-notebook-lifecycle)
+  - [EMR](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#emr)
+  - [From source](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/install.html#from-source)
+- [**At scale**](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/scale.html)
+  - [Getting Started](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/scale.html#getting-started)
+  - [Supported APIs](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/scale.html#supported-apis)
+  - [Resources](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/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)
@@ -156,36 +150,35 @@ The quickest way to get started is to use AWS Glue with Ray. Read our [docs](htt
   - [033 - Amazon Neptune](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/033%20-%20Amazon%20Neptune.ipynb)
   - [034 - Distributing Calls Using Ray](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/034%20-%20Distributing%20Calls%20using%20Ray.ipynb)
   - [035 - Distributing Calls on Ray Remote Cluster](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/035%20-%20Distributing%20Calls%20on%20Ray%20Remote%20Cluster.ipynb)
-  - [036 - Distributing Calls with Glue Interactive Sessions on Ray](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/036%20-%20Distributing%20Calls%20with%20Glue%20Interactive%20Sessions%20on%20Ray.ipynb)
   - [037 - Glue Data Quality](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/037%20-%20Glue%20Data%20Quality.ipynb)
   - [038 - OpenSearch Serverless](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/038%20-%20OpenSearch%20Serverless.ipynb)
   - [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/3.7.2/api.html)
-  - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-s3)
-  - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#aws-glue-catalog)
-  - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-athena)
-  - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-redshift)
-  - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#postgresql)
-  - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#mysql)
-  - [SQL Server](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#sqlserver)
-  - [Oracle](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#oracle)
-  - [Data API Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#data-api-redshift)
-  - [Data API RDS](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#data-api-rds)
-  - [OpenSearch](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#opensearch)
-  - [AWS Glue Data Quality](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#aws-glue-data-quality)
-  - [Amazon Neptune](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-neptune)
-  - [DynamoDB](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#dynamodb)
-  - [Amazon Timestream](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-timestream)
-  - [Amazon EMR](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-emr)
-  - [Amazon CloudWatch Logs](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-cloudwatch-logs)
-  - [Amazon Chime](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-chime)
-  - [Amazon QuickSight](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#amazon-quicksight)
-  - [AWS STS](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#aws-sts)
-  - [AWS Secrets Manager](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#aws-secrets-manager)
-  - [Global Configurations](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#global-configurations)
-  - [Distributed - Ray](https://aws-sdk-pandas.readthedocs.io/en/3.7.2/api.html#distributed-ray)
+- [**API Reference**](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html)
+  - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-s3)
+  - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#aws-glue-catalog)
+  - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-athena)
+  - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-redshift)
+  - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#postgresql)
+  - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#mysql)
+  - [SQL Server](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#sqlserver)
+  - [Oracle](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#oracle)
+  - [Data API Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#data-api-redshift)
+  - [Data API RDS](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#data-api-rds)
+  - [OpenSearch](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#opensearch)
+  - [AWS Glue Data Quality](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#aws-glue-data-quality)
+  - [Amazon Neptune](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-neptune)
+  - [DynamoDB](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#dynamodb)
+  - [Amazon Timestream](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-timestream)
+  - [Amazon EMR](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-emr)
+  - [Amazon CloudWatch Logs](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-cloudwatch-logs)
+  - [Amazon Chime](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-chime)
+  - [Amazon QuickSight](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#amazon-quicksight)
+  - [AWS STS](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#aws-sts)
+  - [AWS Secrets Manager](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#aws-secrets-manager)
+  - [Global Configurations](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/api.html#global-configurations)
+  - [Distributed - Ray](https://aws-sdk-pandas.readthedocs.io/en/3.7.3/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)
 
@@ -198,19 +191,6 @@ You may also find help on these community resources:
   and tag it with `awswrangler`
 * [Runbook](https://github.com/aws/aws-sdk-pandas/discussions/1815) for AWS SDK for pandas with Ray
 
-## Community Resources
-
-Please [send a Pull Request](https://github.com/aws/aws-sdk-pandas/edit/main/README.md) with your resource reference and @githubhandle.
-
-- [YouTube channel](https://www.youtube.com/playlist?list=PL7bE4nSzLSWdDdlfRgfKo2JBplB4p_v5O) [[@AdrianoNicolucci](https://github.com/AdrianoNicolucci)]
-- [Optimize Python ETL by extending Pandas with AWS SDK for pandas](https://aws.amazon.com/blogs/big-data/optimize-python-etl-by-extending-pandas-with-aws-data-wrangler/) [[@igorborgest](https://github.com/igorborgest)]
-- [Reading Parquet Files With AWS Lambda](https://aprakash.wordpress.com/2020/04/14/reading-parquet-files-with-aws-lambda/) [[@anand086](https://github.com/anand086)]
-- [Transform AWS CloudTrail data using AWS SDK for pandas](https://aprakash.wordpress.com/2020/09/17/transform-aws-cloudtrail-data-using-aws-data-wrangler/) [[@anand086](https://github.com/anand086)]
-- [Rename Glue Tables using AWS SDK for pandas](https://ananddatastories.com/rename-glue-tables-using-aws-sdk-pandas/) [[@anand086](https://github.com/anand086)]
-- [Getting started on AWS SDK for pandas and Athena](https://medium.com/@dheerajsharmainampudi/getting-started-on-aws-sdk-pandas-and-athena-7b446c834076) [[@dheerajsharma21](https://github.com/dheerajsharma21)]
-- [Simplifying Pandas integration with AWS data related services](https://medium.com/@bv_subhash/aws-sdk-pandas-simplifying-pandas-integration-with-aws-data-related-services-2b3325c12188) [[@bvsubhash](https://github.com/bvsubhash)]
-- [Build an ETL pipeline using AWS S3, Glue and Athena](https://www.linkedin.com/pulse/build-etl-pipeline-using-aws-s3-glue-athena-data-wrangler-tom-reid/) [[@taupirho](https://github.com/taupirho)]
-
 ## Logging
 
 Enabling internal logging examples:
@@ -228,36 +208,3 @@ Into AWS lambda:
 import logging
 logging.getLogger("awswrangler").setLevel(logging.DEBUG)
 ```
-
-## Who uses AWS SDK for pandas?
-
-Knowing which companies are using this library is important to help prioritize the project internally.
-If you would like us to include your company’s name and/or logo in the README file to indicate that your company is using the AWS SDK for pandas, please raise a "Support Us" issue. If you would like us to display your company’s logo, please raise a linked pull request to provide an image file for the logo. Note that by raising a Support Us issue (and related pull request), you are granting AWS permission to use your company’s name (and logo) for the limited purpose described here and you are confirming that you have authority to grant such permission.
-
-- [Amazon](https://www.amazon.com/)
-- [AWS](https://aws.amazon.com/)
-- [Cepsa](https://cepsa.com) [[@alvaropc](https://github.com/alvaropc)]
-- [Cognitivo](https://www.cognitivo.ai/) [[@msantino](https://github.com/msantino)]
-- [Digio](https://www.digio.com.br/) [[@afonsomy](https://github.com/afonsomy)]
-- [DNX](https://www.dnx.solutions/) [[@DNXLabs](https://github.com/DNXLabs)]
-- [Fortescue Future Industries](https://ffi.com.au/) [[@spencervoorend](https://github.com/spencervoorend)]
-- [Funcional Health Tech](https://www.funcionalcorp.com.br/) [[@webysther](https://github.com/webysther)]
-- [Funding Circle](https://www.fundingcircle.com/) [[@pfig](https://github.com/pfig)]
-- [Infomach](https://www.infomach.com.br/)
-- [Informa Markets](https://www.informamarkets.com/en/home.html) [[@mateusmorato]](http://github.com/mateusmorato)
-- [LINE TV](https://www.linetv.tw/) [[@bryanyang0528](https://github.com/bryanyang0528)]
-- [LogicalCube](https://www.logicalcube.com) [[@zolabud](https://github.com/zolabud)]
-- [Magnataur](https://magnataur.com) [[@brianmingus2](https://github.com/brianmingus2)]
-- [M4U](https://www.m4u.com.br/) [[@Thiago-Dantas](https://github.com/Thiago-Dantas)]
-- [NBCUniversal](https://www.nbcuniversal.com/) [[@vibe](https://github.com/vibe)]
-- [nrd.io](https://nrd.io/) [[@mrtns](https://github.com/mrtns)]
-- [OKRA Technologies](https://okra.ai) [[@JPFrancoia](https://github.com/JPFrancoia), [@schot](https://github.com/schot)]
-- [Pier](https://www.pier.digital/) [[@flaviomax](https://github.com/flaviomax)]
-- [Pismo](https://www.pismo.io/) [[@msantino](https://github.com/msantino)]
-- [ringDNA](https://www.ringdna.com/) [[@msropp](https://github.com/msropp)]
-- [Serasa Experian](https://www.serasaexperian.com.br/) [[@andre-marcos-perez](https://github.com/andre-marcos-perez)]
-- [Shipwell](https://shipwell.com/) [[@zacharycarter](https://github.com/zacharycarter)]
-- [strongDM](https://www.strongdm.com/) [[@mrtns](https://github.com/mrtns)]
-- [Thinkbumblebee](https://www.thinkbumblebee.com/) [[@dheerajsharma21]](https://github.com/dheerajsharma21)
-- [VTEX](https://vtex.com/us-en/) [[@igorborgest]](https://github.com/igorborgest)
-- [Zillow](https://www.zillow.com/) [[@nicholas-miles]](https://github.com/nicholas-miles)

VERSION

@@ -1 +1 @@
-3.7.2
+3.7.3

awswrangler/__metadata__.py

@@ -7,5 +7,5 @@
 
 __title__: str = "awswrangler"
 __description__: str = "Pandas on AWS."
-__version__: str = "3.7.2"
+__version__: str = "3.7.3"
 __license__: str = "Apache License 2.0"

awswrangler/_data_types.py

@@ -46,7 +46,7 @@ def pyarrow2athena(  # noqa: PLR0911,PLR0912
         return "timestamp"
     if pa.types.is_date(dtype):
         return "date"
-    if pa.types.is_binary(dtype):
+    if pa.types.is_binary(dtype) or pa.types.is_fixed_size_binary(dtype):
         return "binary"
     if pa.types.is_dictionary(dtype):
         return pyarrow2athena(dtype=dtype.value_type, ignore_null=ignore_null)
@@ -308,6 +308,7 @@ def _split_map(s: str) -> list[str]:
 
 def athena2pyarrow(dtype: str) -> pa.DataType:  # noqa: PLR0911,PLR0912
     """Athena to PyArrow data types conversion."""
+    dtype = dtype.strip()
     if dtype.startswith(("array", "struct", "map")):
         orig_dtype: str = dtype
     dtype = dtype.lower().replace(" ", "")
@@ -375,7 +376,7 @@ def athena2pandas(dtype: str, dtype_backend: str | None = None) -> str:  # noqa:
         return "decimal" if dtype_backend != "pyarrow" else "double[pyarrow]"
     if dtype in ("binary", "varbinary"):
         return "bytes" if dtype_backend != "pyarrow" else "binary[pyarrow]"
-    if dtype in ("array", "row", "map"):
+    if any(dtype.startswith(t) for t in ["array", "row", "map", "struct"]):
         return "object"
     if dtype == "geometry":
         return "string"