[SPARKNLP-1119] Adding XML reader

[danilojsl]

Description

This pull request introduces a new feature that enables reading and parsing XML files into a structured Spark DataFrame. Leveraging this functionality allows for efficient processing and analysis of XML content, seamlessly integrating with Spark NLP for enhanced downstream natural language processing tasks.

Added sparknlp.read().xml(): This method accepts file paths of XML content.

Use in Partition :

partitioner = Partition(content_type = "application/xml").partition(xml_directory)

Motivation and Context

• Structured Data Representation: By transforming raw XML content into a well-defined DataFrame structure, we enable seamless integration with Spark's powerful analytical and data processing capabilities.

• Scalability: Leveraging Spark’s distributed architecture, this feature supports the efficient processing of large volumes of XML data, critical for big data and enterprise-level NLP workflows.

• Simplified Data Manipulation: A structured DataFrame representation of XML simplifies common data manipulation tasks such as filtering, aggregation, and transformation, thereby reducing complexity and improving productivity.

• Enhanced Context for LLM Tasks: Converting XML documents into structured formats allows for more precise content extraction and context-aware processing, enhancing prompt quality and relevance for large language models (LLMs) in downstream NLP applications like information retrieval, question answering, and summarization.

How Has This Been Tested?

Screenshots (if appropriate):

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• Code improvements with no or little impact
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)

Checklist:

• My code follows the code style of this project.
• My change requires a change to the documentation.
• I have updated the documentation accordingly.
• I have read the CONTRIBUTING page.
• I have added tests to cover my changes.
• All new and existing tests passed.