feat: added new database.getSize() api

[lvca]

What does this PR do?

A brief description of the change being made with this pull request.

Motivation

What inspired you to submit this pull request?

Related issues

A list of issues either fixed, containing architectural discussions, otherwise relevant
for this Pull Request.

Additional Notes

Anything else we should know when reviewing?

Checklist

• I have run the build using mvn clean package command
• My unit tests cover both failure and success scenarios

[gemini-code-assist]

Summary of Changes

Hello @lvca, I'm Gemini Code Assist¹! 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 introduces a new API to determine the total size of a database on disk. This feature provides a straightforward way to monitor the storage consumption of a database instance, which can be crucial for resource management and capacity planning. The implementation carefully aggregates file sizes within the database directory, and its functionality is thoroughly validated with new unit tests.

Highlights

• New database.getSize() API: A new getSize() method has been added to the BasicDatabase and DatabaseInternal interfaces, allowing users to query the total disk space occupied by a database.
• Implementation in LocalDatabase: The getSize() method is implemented in LocalDatabase to calculate the cumulative size of all regular files within the database's directory, providing an accurate measure of its footprint.
• Comprehensive Unit Tests: A new test file, DatabaseGetSizeTest.java, has been introduced with extensive unit tests covering various scenarios for the getSize() API, including empty databases, databases with documents, vertices, edges, and indexes, and behavior after data deletion.
• API Delegation in Server Components: The new getSize() API has been integrated into ServerDatabase and ReplicatedDatabase by delegating the call to their respective wrapped or proxied database instances, ensuring consistent functionality across different deployment contexts.

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 👍 and 👎 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.

Footnotes

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. ↩

[mergify]

🧪 CI Insights

Here's what we observed from your CI run for 272e5ab.

🟢 All jobs passed!

But CI Insights is watching 👀

[gemini-code-assist]

Code Review

This pull request introduces a new database.getSize() API to calculate the total size of the database files on disk. The implementation in LocalDatabase correctly walks the database directory and sums the sizes of all files. The new API is also exposed through the ServerDatabase and ReplicatedDatabase wrappers, and a comprehensive set of unit tests has been added to validate the new functionality. The changes are well-implemented, but I have one suggestion to improve the consistency of exception handling in the getSize() method.

[gemini-code-assist]

The exception handling in this block could be more consistent. An IOException thrown by Files.walk(dir) is not caught here and would be handled by the outer executeInReadLock method, leading to a generic error message. In contrast, an IOException from Files.size(p) is wrapped in UncheckedIOException and caught, resulting in a more specific error message.

To ensure all I/O errors during size calculation are handled uniformly with a clear message, I suggest catching both IOException and UncheckedIOException within this block.

      try {
        final Path dir = Path.of(databasePath);
        if (!Files.exists(dir))
          return 0L;

        try (Stream<Path> stream = Files.walk(dir)) {
          return stream.filter(Files::isRegularFile).mapToLong(p -> {
            try {
              return Files.size(p);
            } catch (IOException e) {
              throw new UncheckedIOException(e);
            }
          }).sum();
        }
      } catch (IOException e) {
        throw new DatabaseOperationException("Error calculating database size", e);
      } catch (UncheckedIOException e) {
        throw new DatabaseOperationException("Error calculating database size", e.getCause());
      }