Bq timestamp schema conversion

[claudevdm]

1. Adds ability to map BQ TIMESTAMP(12) columns to either Timestamp.MILLIS, Timestamp.MICROS, Timestamp.NANOS or string for picosecond precision. This is used in the direct read path where a user specifies the precision of the timestamp that the read API returns. E.g. if a user reads with nanosecond precision, TIMESTAMP(12) columns will be mapped to beam LogicalTypes.Timestamp.NANOS etc.
2. Adds conversion from BQ TableRow timestamps (formatted as UTC strings) to beam rows (where timestamp is a Timestamp logical type

Note: A TimestampPrecision.java enum is added because it will be reused for future PR's (e.g. specifying the desired read precision).

Thank you for your contribution! Follow this checklist to help us incorporate your contribution quickly and easily:

• [ ] Mention the appropriate issue in your description (for example: addresses #123), if applicable. This will automatically add a link to the pull request in the issue. If you would like the issue to automatically close on merging the pull request, comment fixes #<ISSUE NUMBER> instead.
• [ ] Update CHANGES.md with noteworthy changes.
• [ ] If this contribution is large, please file an Apache Individual Contributor License Agreement.

See the Contributor Guide for more tips on how to make review process smoother.

To check the build health, please visit https://github.com/apache/beam/blob/master/.test-infra/BUILD_STATUS.md

GitHub Actions Tests Status (on master branch)

See CI.md for more information about GitHub Actions CI or the workflows README to see a list of phrases to trigger workflows.

[gemini-code-assist[bot]]

Summary of Changes

Hello @claudevdm, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances Apache Beam's integration with BigQuery by providing more granular control over how high-precision timestamp data is handled. It allows users to define the desired precision when converting BigQuery's TIMESTAMP(12) columns into Beam's schema types, ensuring data integrity and flexibility for applications requiring specific timestamp resolutions. The changes also refine the internal mechanisms for parsing and formatting timestamp values between BigQuery and Beam's data models.

Highlights

• BigQuery TIMESTAMP(12) Mapping: Adds the capability to map BigQuery TIMESTAMP(12) columns, which offer picosecond precision, to various Beam logical timestamp types: Timestamp.MILLIS, Timestamp.MICROS, Timestamp.NANOS, or as a STRING type to preserve full precision.
• Timestamp Conversion: Introduces improved conversion logic for timestamps, allowing BigQuery TableRow timestamps (formatted as UTC strings) to be accurately mapped to Beam rows with the appropriate Timestamp logical type.
• Configurable Precision: A new TimestampPrecision enum and a picosecondTimestampMapping option have been added to BigQueryUtils.SchemaConversionOptions, enabling users to specify the desired precision for TIMESTAMP(12) columns, defaulting to nanoseconds.
• Variable Precision Formatter: A new VAR_PRECISION_FORMATTER is introduced to handle parsing of timestamp strings with varying numbers of decimal places for nanoseconds, ensuring robust conversion from BigQuery string representations to Java Instant objects.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

[^1]: Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

[claudevdm]

/gemini review

[claudevdm]

R: @Abacn

[claudevdm]

R: @ahmedabu98

[github-actions[bot]]

Stopping reviewer notifications for this pull request: review requested by someone other than the bot, ceding control. If you'd like to restart, comment assign set of reviewers

[github-actions[bot]]

Stopping reviewer notifications for this pull request: review requested by someone other than the bot, ceding control. If you'd like to restart, comment assign set of reviewers