out_s3: Add a description for pure C parquet

[cosmo0920]

Corresponding of fluent/fluent-bit#10691.

Summary by CodeRabbit

• Documentation
  • Corrected S3 reference link and clarified compression/format options and availability
  • Added comprehensive Parquet guidance: build requirements, enablement steps, testing examples, and usage notes (including upload/encoding considerations)
  • Clarified gzip content-encoding guidance and provided example configurations for validation and testing

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[cosmo0920]

@esmerel Good morning.
Vale warns some of usages that include Parquet is not following sentence style of capitalization. But Parquet is a proper noun. How do we handle on such warnings?

[eschabell]

@esmerel review needed, see questions above.

[esmerel]

@esmerel Good morning. Vale warns some of usages that include Parquet is not following sentence style of capitalization. But Parquet is a proper noun. How do we handle on such warnings?

We add it to the spelling exceptions file for Vale. I went ahead and did that in #2116 =)

And also the heading file, which I should have realized. #2117

[esmerel]

one suggestion that looks accidental

[patrick-stephens]

Looks fine other than adding the legacy format config as well.

[coderabbitai]

Walkthrough

Updates to the S3 output documentation: corrects the S3 guide link, replaces the compression parameter description with a combined "Compression/format" explanation, and adds detailed Parquet support instructions, build/testing examples, usage notes, and a duplicated Parquet block plus a minor tab/blank formatting tweak.

Changes

Cohort / File(s)

Summary

S3 Documentation Updates pipeline/outputs/s3.md

Replaced CloudWatch S3 link with official Amazon S3 user guide; changed compression listing to a combined "Compression/format" section clarifying Arrow/build-time options and gzip/Content-Encoding behavior; added explicit Parquet support requirements and an "Enable Parquet support" section with build steps, testing configurations and examples (YAML and conf), usage notes about PutObject vs multipart uploads; duplicated Parquet enablement block and added a minor tab/blank formatting adjustment.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

• Focus review on accuracy of build and dependency instructions for Parquet (Arrow, GLib/Parquet GLib) and correctness of example configurations.
• Verify the duplicated Parquet block is intentional; consider removing duplicate.
• Check the added note on gzip Content-Encoding for clarity and correctness.
• Confirm the updated S3 user guide URL is correct.

Poem

🐇 I hopped through docs with nimble feet,
I fixed a link and made guide neat.
Parquet paths I tucked in tight,
Compress and test — the examples light.
A joyful nibble — docs take flight! 🥕✨

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title 'out_s3: Add a description for pure C parquet' is directly related to the changeset, which adds documentation describing Parquet support (including pure C Parquet options) for the S3 output plugin.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch cosmo0920-add-parquet-c-description-for-out_s3

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 2dee9d8 and 0e3ab85.

📒 Files selected for processing (1)

• pipeline/outputs/s3.md (4 hunks)

🔇 Additional comments (3)

pipeline/outputs/s3.md (3)

700-723: LGTM on build requirements documentation.

The Parquet build requirements section is clear and actionable, with a concrete Ubuntu/Debian example and proper references to external documentation for other distributions.

---

728-783: LGTM on testing configurations.

The example configurations for Parquet testing are well-structured, providing both YAML and conf formats with appropriate settings for testing (debug logging, dummy input with diverse data types, and use_put_object enabled).

---

700-783: Verify: Has the legacy format request been addressed?

A previous review comment from patrick-stephens requested: "We should add the legacy format as well." The current Parquet section doesn't explicitly mention legacy compression formats or other format options.

Please clarify:

1. Does this PR need to document additional compression formats beyond gzip and parquet?
2. If so, should they be added to this section or elsewhere in the documentation?

[coderabbitai]

Actionable comments posted: 1

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 0e3ab85 and 848e027.

📒 Files selected for processing (1)

• pipeline/outputs/s3.md (4 hunks)

🔇 Additional comments (4)

pipeline/outputs/s3.md (4)

9-9: ✓ Helpful documentation link update.

The change from the CloudWatch Logs S3 link to the official AWS S3 user guide is more appropriate and direct for users referencing S3 capabilities.

---

39-39: ✓ Comprehensive compression parameter documentation.

The expanded compression description clearly distinguishes between:

• Always-available formats (gzip with Content-Encoding header behavior)
• Build-time conditional formats (parquet requiring -DFLB_ARROW=On and Arrow GLib/Parquet GLib)
• Typical usage patterns (Parquet with use_put_object On)

This is precise and helpful for users evaluating their build configuration.

---

700-722: ✓ Clear build requirements and instructions for Parquet support.

The new "Build requirements for Parquet" section provides:

• Specific package installation steps for Ubuntu/Debian
• CMake command with the required -DFLB_ARROW=On flag
• Reference to upstream Apache Parquet installation docs for other distributions

This guidance aligns well with the parameter documentation and enables users to set up Parquet correctly.

---

724-781: ✓ Thorough testing section with dual-format examples.

The "Testing Parquet support" section includes:

• Complete service and pipeline configuration in both YAML and text (.conf) formats
• Realistic input (dummy input with mixed data types)
• Key Parquet-specific settings (compression: parquet, use_put_object: On)
• Comments noting where additional parameters can be added

Examples are clear and actionable.

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Remove extraneous blank line in tab markup.

Line 642 contains a blank line immediately after the opening {% tabs %} tag, which appears to be a formatting artifact. This extra whitespace can affect the rendered tab display.

  {% tabs %}
-
  {% tab title="fluent-bit.yaml" %}

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	{% tabs %}
	{% tab title="fluent-bit.yaml" %}

🤖 Prompt for AI Agents

In pipeline/outputs/s3.md around line 642, there is an extraneous blank line
immediately after the opening `{% tabs %}` tag; remove that blank line so the
first tab block/content follows the `{% tabs %}` tag directly (ensure no other
whitespace-only lines exist between the `{% tabs %}` tag and the first `{% tab
%}` or tab content).